Daily Papers

Long context inference presents challenges at the system level with increased compute and memory requirements, as well as from an accuracy perspective in being able to reason over long contexts. Recently, several methods have been proposed to compress the prompt to reduce the context length. However, there has been little work on comparing the different proposed methods across different tasks through a standardized analysis. This has led to conflicting results. To address this, here we perform a comprehensive characterization and evaluation of different prompt compression methods. In particular, we analyze extractive compression, summarization-based abstractive compression, and token pruning methods. Surprisingly, we find that extractive compression often outperforms all the other approaches, and enables up to 10x compression with minimal accuracy degradation. Interestingly, we also find that despite several recent claims, token pruning methods often lag behind extractive compression. We only found marginal improvements on summarization tasks.

Long-context inference for Large Language Models (LLMs) is heavily limited by high computational demands. While several existing methods optimize attention computation, they still process the full set of hidden states at each layer, limiting overall efficiency. In this work, we propose SlimInfer, an innovative framework that aims to accelerate inference by directly pruning less critical prompt tokens during the forward pass. Our key insight is an information diffusion phenomenon: As information from critical tokens propagates through layers, it becomes distributed across the entire sequence. This diffusion process suggests that LLMs can maintain their semantic integrity when excessive tokens, even including these critical ones, are pruned in hidden states. Motivated by this, SlimInfer introduces a dynamic fine-grained pruning mechanism that accurately removes redundant tokens of hidden state at intermediate layers. This layer-wise pruning naturally enables an asynchronous KV cache manager that prefetches required token blocks without complex predictors, reducing both memory usage and I/O costs. Extensive experiments show that SlimInfer can achieve up to 2.53times time-to-first-token (TTFT) speedup and 1.88times end-to-end latency reduction for LLaMA3.1-8B-Instruct on a single RTX 4090, without sacrificing performance on LongBench. Our code will be released upon acceptance.

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference, particularly in managing key-value (KV) caches, presents significant efficiency challenges. While Speculative Decoding (SD) traditionally accelerates inference using smaller draft models, its effectiveness diminishes substantially in long-context scenarios due to memory-bound KV cache operations. We present Retrieval-Augmented Speculative Decoding (RAPID), which leverages RAG for both accelerating and enhancing generation quality in long-context inference. RAPID introduces the RAG drafter-a draft LLM operating on shortened retrieval contexts-to speculate on the generation of long-context target LLMs. Our approach enables a new paradigm where same-scale or even larger LLMs can serve as RAG drafters while maintaining computational efficiency. To fully leverage the potentially superior capabilities from stronger RAG drafters, we develop an inference-time knowledge transfer dynamic that enriches the target distribution by RAG. Extensive experiments on the LLaMA-3.1 and Qwen2.5 backbones demonstrate that RAPID effectively integrates the strengths of both approaches, achieving significant performance improvements (e.g., from 39.33 to 42.83 on InfiniteBench for LLaMA-3.1-8B) with more than 2x speedups. Our analyses reveal that RAPID achieves robust acceleration beyond 32K context length and demonstrates superior generation quality in real-world applications.

While long-context inference is crucial for advancing large language model (LLM) applications, its prefill speed remains a significant bottleneck. Current approaches, including sequence parallelism strategies and compute reduction through approximate attention mechanisms, still fall short of delivering optimal inference efficiency. This hinders scaling the inputs to longer sequences and processing long-context queries in a timely manner. To address this, we introduce APB, an efficient long-context inference framework that leverages multi-host approximate attention to enhance prefill speed by reducing compute and enhancing parallelism simultaneously. APB introduces a communication mechanism for essential key-value pairs within a sequence parallelism framework, enabling a faster inference speed while maintaining task performance. We implement APB by incorporating a tailored FlashAttn kernel alongside optimized distribution strategies, supporting diverse models and parallelism configurations. APB achieves speedups of up to 9.2x, 4.2x, and 1.6x compared with FlashAttn, RingAttn, and StarAttn, respectively, without any observable task performance degradation. We provide the implementation and experiment code of APB in https://github.com/thunlp/APB.

Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and the high computational complexity of attention create significant bottlenecks in memory usage and latency. In this paper, we find that attention in diverse long-context tasks exhibits sparsity, and LLMs implicitly "know" which tokens can be dropped or evicted at the head level after the pre-filling stage. Based on this insight, we propose Self-Attention Guided Eviction~(SAGE-KV), a simple and effective KV eviction cache method for long-context inference. After prefilling, our method performs a one-time top-k selection at both the token and head levels to compress the KV cache, enabling efficient inference with the reduced cache. Evaluations on LongBench and three long-context LLMs (Llama3.1-8B-Instruct-128k, Llama3-8B-Prolong-512k-Instruct, and Qwen2.5-7B-Instruct-128k) show that SAGE-KV maintains accuracy comparable to full attention while significantly improving efficiency. Specifically, SAGE-KV achieves 4x higher memory efficiency with improved accuracy over the static KV cache selection method StreamLLM, and 2x higher memory efficiency with better accuracy than the dynamic KV cache selection method Quest.

Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time efficiency. Unlike single-modality LLMs that manage only textual contexts, the KV cache of long-context MLLMs includes representations from multiple images with temporal and spatial relationships and related textual contexts. The predominance of image tokens means traditional optimizations for LLMs' KV caches are unsuitable for multimodal long-context settings, and no prior works have addressed this challenge. In this work, we introduce LOOK-M, a pioneering, fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache. We observe that during prompt prefill, the model prioritizes more textual attention over image features, and based on the multimodal interaction observation, a new proposed text-prior method is explored to compress the KV cache. Furthermore, to mitigate the degradation of image contextual information, we propose several compensatory strategies using KV pairs merging. LOOK-M demonstrates that with a significant reduction in KV Cache memory usage, such as reducing it by 80% in some cases, it not only achieves up to 1.5x faster decoding but also maintains or even enhances performance across a variety of long context multimodal tasks.

The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV cache. However, loading the entire cache incurs significant latency due to PCIe bandwidth bottlenecks in CPU-GPU communication, while aggressive compression causes notable performance degradation. We identify that certain layers in the LLM need to maintain global information and are unsuitable for selective loading. In contrast, other layers primarily focus on a few tokens with dominant activations that potentially incur substantial quantization error. This observation leads to a key insight that loading dominant tokens and quantizing all tokens can complement each other. Building on this insight, we propose a hybrid compression method, TailorKV, which seamlessly integrates quantization and offloading. TailorKV develops an inference framework along with a hardware-friendly implementation that leverages these complementary characteristics. Extensive long-context evaluations exhibit that TailorKV achieves nearly lossless performance under aggressive compression settings, outperforming the state-of-the-art. Particularly, the Llama-3.1-8B with 128k context can be served within a single RTX 3090 GPU, reaching 82 ms per token during decoding.

There is growing demand for performing inference with hundreds of thousands of input tokens on trained transformer models. Inference at this extreme scale demands significant computational resources, hindering the application of transformers at long contexts on commodity (i.e not data center scale) hardware. To address the inference time costs associated with running self-attention based transformer language models on long contexts and enable their adoption on widely available hardware, we propose a tunable mechanism that reduces the cost of the forward pass by attending to only the most relevant tokens at every generation step using a top-k selection mechanism. We showcase the efficiency gains afforded by our method by performing inference on context windows up to 1M tokens using approximately 16GB of GPU RAM. Our experiments reveal that models are capable of handling the sparsity induced by the reduced number of keys and values. By attending to less than 2% of input tokens, we achieve over 95% of model performance on common benchmarks (RULER, AlpacaEval, and Open LLM Leaderboard).

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache pruning methods either damage the long-context capabilities of LLMs or offer only limited efficiency improvements. In this paper, we identify that only a fraction of attention heads, a.k.a, Retrieval Heads, are critical for processing long contexts and require full attention across all tokens. In contrast, all other heads, which primarily focus on recent tokens and attention sinks--referred to as Streaming Heads--do not require full attention. Based on this insight, we introduce DuoAttention, a framework that only applies a full KV cache to retrieval heads while using a light-weight, constant-length KV cache for streaming heads, which reduces both LLM's decoding and pre-filling memory and latency without compromising its long-context abilities. DuoAttention uses a lightweight, optimization-based algorithm with synthetic data to identify retrieval heads accurately. Our method significantly reduces long-context inference memory by up to 2.55x for MHA and 1.67x for GQA models while speeding up decoding by up to 2.18x and 1.50x and accelerating pre-filling by up to 1.73x and 1.63x for MHA and GQA models, respectively, with minimal accuracy loss compared to full attention. Notably, combined with quantization, DuoAttention enables Llama-3-8B decoding with 3.3 million context length on a single A100 GPU. Code is provided in https://github.com/mit-han-lab/duo-attention.

To reduce memory costs in long-context inference with Large Language Models (LLMs), many recent works focus on compressing the key-value (KV) cache of different tokens. However, we identify that the previous KV cache compression methods measure token importance individually, neglecting the dependency between different tokens in the real-world language characterics. In light of this, we introduce ChunkKV, grouping the tokens in a chunk as a basic compressing unit, and retaining the most informative semantic chunks while discarding the less important ones. Furthermore, observing that ChunkKV exhibits higher similarity in the preserved indices across different layers, we propose layer-wise index reuse to further reduce computational overhead. We evaluated ChunkKV on cutting-edge long-context benchmarks including LongBench and Needle-In-A-HayStack, as well as the GSM8K and JailbreakV in-context learning benchmark. Our experiments with instruction tuning and multi-step reasoning (O1 and R1) LLMs, achieve up to 10\% performance improvement under aggressive compression ratios compared to existing methods.

The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical portions of the context to optimally approximate Full Attention (FA) through Key-Value (KV) compression or Sparse Attention (SA), enabling the processing of virtually unlimited text lengths in a streaming manner. However, these methods struggle to achieve performance levels comparable to FA, particularly in retrieval tasks. In this paper, our analysis of attention head patterns reveals that LLMs' attention distributions show strong local correlations, naturally reflecting a chunking mechanism for input context. We propose Ltri-LLM framework, which divides KVs into spans, stores them in an offline index, and retrieves the relevant KVs into memory for various queries. Experimental results on popular long text benchmarks show that Ltri-LLM can achieve performance close to FA while maintaining efficient, streaming-based inference.

With the development of large language models (LLMs), the ability to handle longer contexts has become a key capability for Web applications such as cross-document understanding and LLM-powered search systems. However, this progress faces two major challenges: performance degradation due to sequence lengths out-of-distribution, and excessively long inference times caused by the quadratic computational complexity of attention. These issues hinder the application of LLMs in long-context scenarios. In this paper, we propose Dynamic Token-Level KV Cache Selection (TokenSelect), a model-agnostic, training-free method for efficient and accurate long-context inference. TokenSelect builds upon the observation of non-contiguous attention sparsity, using Query-Key dot products to measure per-head KV Cache criticality at token-level. By per-head soft voting mechanism, TokenSelect selectively involves a small number of critical KV cache tokens in the attention calculation without sacrificing accuracy. To further accelerate TokenSelect, we designed the Selection Cache based on observations of consecutive Query similarity and implemented efficient dot product kernel, significantly reducing the overhead of token selection. A comprehensive evaluation of TokenSelect demonstrates up to 23.84x speedup in attention computation and up to 2.28x acceleration in end-to-end latency, while providing superior performance compared to state-of-the-art long-context inference methods.

Emerging Large Language Model (LLM) applications require long input prompts to perform complex downstream tasks like document analysis and code generation. For these long context length applications, the length of the input prompt poses a significant challenge in terms of inference efficiency since the inference costs increase linearly with sequence length. However, for many of these applications, much of the context in the prompt is fixed across different user inputs, thereby providing the opportunity to perform offline optimizations to process user inputs quickly, as they are received. In this work, we propose Squeezed Attention as a mechanism to accelerate LLM applications where a large portion of the input prompt is fixed. We first leverage K-means clustering offline to group the keys for the fixed context based on semantic similarity and represent each cluster with a single centroid value. During inference, we compare query tokens from the user input with the centroids to predict which of the keys from the fixed context are semantically relevant and need to be loaded during inference. We then compute exact attention using only these important keys from the fixed context, thereby reducing bandwidth and computational costs. We also extend our method to use a hierarchical centroid lookup to identify important keys, which can reduce the complexity of attention from linear to logarithmic with respect to the context length. We implement optimized Triton kernels for centroid comparison and sparse FlashAttention with important keys, achieving more than 4x speedups during both the prefill and generation phases for long-context inference. Furthermore, we have extensively evaluated our method on various long-context benchmarks including LongBench, where it achieves a 3x reduction in KV cache budget without accuracy loss and up to an 8x reduction with <0.5 point accuracy gap for various models.

Large language models (LLMs) have shown remarkable advances in supporting long-context comprehension and processing tasks. However, scaling the generation inference of LLMs to such long contexts incurs significant additional computation load, and demands a substantial GPU memory footprint to maintain the key-value (KV) cache of transformer-based LLMs. Existing KV cache compression methods, such as quantization, face memory bottlenecks as context length increases, while static-sized caches, such as eviction, suffer from inefficient policies. These limitations restrict deployment on consumer-grade devices like a single Nvidia 4090 GPU. To overcome this, we propose Locret, a framework for long-context LLM inference that introduces retaining heads to evaluate the causal importance of KV cache units, allowing for more accurate eviction within a fixed cache size. Locret is fine-tuned on top of the frozen backbone LLM using a minimal amount of data from standard long-context SFT datasets. During inference, we evict low-importance cache units along with a chunked prefill pattern, significantly reducing peak GPU memory usage. We conduct an extensive empirical study to evaluate Locret, where the experimental results show that Locret outperforms the recent competitive approaches, including InfLLM, Quantization, SirLLM, and MInference, in terms of memory efficiency and the quality of generated contents -- Locret achieves over a 20x and 8x KV cache compression ratio compared to the full KV cache for Phi-3-mini-128K and Llama-3.1-8B-instruct. Additionally, Locret can be combined with other methods, such as quantization and token merging. To our knowledge, Locret is the first framework capable of deploying Llama-3.1-8B or similar models on a single Nvidia 4090 GPU, enabling 128K long-context inference without compromising generation quality, and requiring little additional system optimizations.

Retrieval-Augmented Language Modeling (RALM) by integrating large language models (LLM) with relevant documents from an external corpus is a proven method for enabling the LLM to generate information beyond the scope of its pre-training corpus. Previous work using utilizing retrieved content by simply prepending retrieved contents to the input poses a high runtime issue, which degrades the inference efficiency of the LLMs because they fail to use the Key-Value (KV) cache efficiently. In this paper, we propose FlashBack, a modular RALM designed to improve the inference efficiency of RALM with appending context pattern while maintaining decent performance after specific fine-tuning without heavily destruct the knowledge integrity of the LLM. FlashBack appends retrieved documents at the end of the context for efficiently utilizing the KV cache instead of prepending them. Our experiment shows that the inference speed of FlashBack is up to 4times faster than the prepending method on a 7B LLM (Llama 2). Via bypassing unnecessary re-computation, it demonstrates an advancement by achieving significantly faster inference speed, and this heightened efficiency will substantially reduce inferential cost. Our code will be publicly available.

Large language models (LLMs) now support context windows of hundreds of thousands to millions of tokens, enabling applications such as long-document summarization, large-scale code synthesis, multi-document question answering and persistent multi-turn dialogue. However, such extended contexts exacerbate the quadratic cost of self-attention, leading to severe latency in autoregressive decoding. Existing sparse attention methods alleviate these costs but rely on heuristic patterns that struggle to recall critical key-value (KV) pairs for each query, resulting in accuracy degradation. We introduce Adamas, a lightweight yet highly accurate sparse attention mechanism designed for long-context inference. Adamas applies the Hadamard transform, bucketization and 2-bit compression to produce compact representations, and leverages Manhattan-distance estimation for efficient top-k selections. Experiments show that Adamas matches the accuracy of full attention with only a 64-token budget, achieves near-lossless performance at 128, and supports up to 8x higher sparsity than prior state-of-the-art (SOTA) methods while delivering up to 4.4x self-attention and 1.5x end-to-end speedups on 32K-length sequences. Remarkably, Adamas attains comparable or even lower perplexity than full attention, underscoring its effectiveness in maintaining accuracy under aggressive sparsity.

Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes \sysname, an adaptive sublayer skipping method specifically designed for long-context inference. \sysname adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of \sysname is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.

Although applications involving long-context inputs are crucial for the effective utilization of large language models (LLMs), they also result in increased computational costs and reduced performance. To address this challenge, we propose an efficient, training-free prompt compression method that retains key information within compressed prompts. We identify specific attention heads in transformer-based LLMs, which we designate as evaluator heads, that are capable of selecting tokens in long inputs that are most significant for inference. Building on this discovery, we develop EHPC, an Evaluator Head-based Prompt Compression method, which enables LLMs to rapidly "skim through" input prompts by leveraging only the first few layers with evaluator heads during the pre-filling stage, subsequently passing only the important tokens to the model for inference. EHPC achieves state-of-the-art results across two mainstream benchmarks: prompt compression and long-context inference acceleration. Consequently, it effectively reduces the complexity and costs associated with commercial API calls. We further demonstrate that EHPC attains competitive results compared to key-value cache-based acceleration methods, thereby highlighting its potential to enhance the efficiency of LLMs for long-context tasks.

AlayaDB is a cutting-edge vector database system natively architected for efficient and effective long-context inference for Large Language Models (LLMs) at AlayaDB AI. Specifically, it decouples the KV cache and attention computation from the LLM inference systems, and encapsulates them into a novel vector database system. For the Model as a Service providers (MaaS), AlayaDB consumes fewer hardware resources and offers higher generation quality for various workloads with different kinds of Service Level Objectives (SLOs), when comparing with the existing alternative solutions (e.g., KV cache disaggregation, retrieval-based sparse attention). The crux of AlayaDB is that it abstracts the attention computation and cache management for LLM inference into a query processing procedure, and optimizes the performance via a native query optimizer. In this work, we demonstrate the effectiveness of AlayaDB via (i) three use cases from our industry partners, and (ii) extensive experimental results on LLM inference benchmarks.

Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. Previous research shows that using test-time learning to encode context directly into model parameters can effectively enable reasoning over noisy information. However, meta-learning methods for enabling test-time learning are prohibitively memory-intensive, preventing their application to long context settings. In this work, we propose PERK (Parameter Efficient Reasoning over Knowledge), a scalable approach for learning to encode long input contexts using gradient updates to a lightweight model adapter at test time. Specifically, PERK employs two nested optimization loops in a meta-training phase. The inner loop rapidly encodes contexts into a low-rank adapter (LoRA) that serves as a parameter-efficient memory module for the base model. Concurrently, the outer loop learns to use the updated adapter to accurately recall and reason over relevant information from the encoded long context. Our evaluations on several long-context reasoning tasks show that PERK significantly outperforms the standard prompt-based long-context baseline, achieving average absolute performance gains of up to 90% for smaller models (GPT-2) and up to 27% for our largest evaluated model, Qwen-2.5-0.5B. In general, PERK is more robust to reasoning complexity, length extrapolation, and the locations of relevant information in contexts. Finally, we show that while PERK is memory-intensive during training, it scales more efficiently at inference time than prompt-based long-context inference.

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this capability. Speculative decoding (SD) offers a promising lossless acceleration technique compared to lossy alternatives such as quantization and model cascades. However, most state-of-the-art SD methods are trained on short texts (typically fewer than 4k tokens), making them unsuitable for long-context scenarios. Specifically, adapting these methods to long contexts presents three key challenges: (1) the excessive memory demands posed by draft models due to large Key-Value (KV) cache; (2) performance degradation resulting from the mismatch between short-context training and long-context inference; and (3) inefficiencies in tree attention mechanisms when managing long token sequences. This work introduces LongSpec, a framework that addresses these challenges through three core innovations: a memory-efficient draft model with a constant-sized KV cache; novel position indices that mitigate the training-inference mismatch; and an attention aggregation strategy that combines fast prefix computation with standard tree attention to enable efficient decoding. Experimental results confirm the effectiveness of LongSpec, achieving up to a 3.26x speedup over strong Flash Attention baselines across five long-context understanding datasets, as well as a 2.25x reduction in wall-clock time on the AIME24 long reasoning task with the QwQ model, demonstrating significant latency improvements for long-context applications. The code is available at https://github.com/sail-sg/LongSpec.

Long-context LLMs have enabled numerous downstream applications but also introduced significant challenges related to computational and memory efficiency. To address these challenges, optimizations for long-context inference have been developed, centered around the KV cache. However, existing benchmarks often evaluate in single-request, neglecting the full lifecycle of the KV cache in real-world use. This oversight is particularly critical, as KV cache reuse has become widely adopted in LLMs inference frameworks, such as vLLM and SGLang, as well as by LLM providers, including OpenAI, Microsoft, Google, and Anthropic. To address this gap, we introduce SCBench(SharedContextBench), a comprehensive benchmark for evaluating long-context methods from a KV cachecentric perspective: 1) KV cache generation, 2) KV cache compression, 3) KV cache retrieval, 4) KV cache loading. Specifically, SCBench uses test examples with shared context, ranging 12 tasks with two shared context modes, covering four categories of long-context capabilities: string retrieval, semantic retrieval, global information, and multi-task. With it, we provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs, Mamba-Attention hybrids, and efficient methods such as sparse attention, KV cache dropping, quantization, retrieval, loading, and prompt compression. The evaluation is conducted on 8 long-context LLMs. Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n^2) pre-filling computation perform robustly. Dynamic sparsity yields more expressive KV caches than static patterns, and layer-level sparsity in hybrid architectures reduces memory usage with strong performance. Additionally, we identify attention distribution shift issues in long-generation scenarios. https://aka.ms/SCBench.

As large language models (LLMs) evolve to handle increasingly longer contexts, serving inference requests for context lengths in the range of millions of tokens presents unique challenges. While existing techniques are effective for training, they fail to address the unique challenges of inference, such as varying prefill and decode phases and their associated latency constraints - like Time to First Token (TTFT) and Time Between Tokens (TBT). Furthermore, there are no long context inference solutions that allow batching requests to increase the hardware utilization today. In this paper, we propose three key innovations for efficient interactive long context LLM inference, without resorting to any approximation: adaptive chunking to reduce prefill overheads in mixed batching, Sequence Pipeline Parallelism (SPP) to lower TTFT, and KV Cache Parallelism (KVP) to minimize TBT. These contributions are combined into a 3D parallelism strategy, enabling Mnemosyne to scale interactive inference to context lengths at least up to 10 million tokens with high throughput enabled with batching. To our knowledge, Mnemosyne is the first to be able to achieve support for 10 million long context inference efficiently, while satisfying production-grade SLOs on TBT (30ms) on contexts up to and including 10 million.

Long-context processing has become a fundamental capability for large language models~(LLMs). To assess model's long-context performance, numerous long-context evaluation benchmarks have been proposed. However, variations in evaluation settings across these benchmarks lead to inconsistent results, making it difficult to draw reliable comparisons. Besides, the high computational cost of long-context evaluation poses a significant barrier for the community to conduct comprehensive assessments of long-context models. In this paper, we propose LOOM-Scope, a comprehensive and efficient framework for long-context evaluation. LOOM-Scope standardizes evaluation settings across diverse benchmarks, supports deployment of efficient long-context inference acceleration methods, and introduces a holistic yet lightweight benchmark suite to evaluate models comprehensively. Homepage: https://loomscope.github.io

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory footprint grows linearly with sequence length and dominates latency at each decoding step. While recent KV cache compression methods identify and load important tokens, they focus predominantly on input contexts and fail to address the cumulative attention errors that arise during long decoding. In this paper, we introduce RetroAttention, a novel KV cache update technique that retrospectively revises past attention outputs using newly arrived KV entries from subsequent decoding steps. By maintaining a lightweight output cache, RetroAttention enables past queries to efficiently access more relevant context, while incurring minimal latency overhead. This breaks the fixed-attention-output paradigm and allows continual correction of prior approximations. Extensive experiments on long-generation benchmarks show that RetroAttention consistently outperforms state-of-the-art (SOTA) KV compression methods, increasing effective KV exposure by up to 1.6times and accuracy by up to 21.9\%.

In this technical report, we present the Ring-linear model series, specifically including Ring-mini-linear-2.0 and Ring-flash-linear-2.0. Ring-mini-linear-2.0 comprises 16B parameters and 957M activations, while Ring-flash-linear-2.0 contains 104B parameters and 6.1B activations. Both models adopt a hybrid architecture that effectively integrates linear attention and softmax attention, significantly reducing I/O and computational overhead in long-context inference scenarios. Compared to a 32 billion parameter dense model, this series reduces inference cost to 1/10, and compared to the original Ring series, the cost is also reduced by over 50%. Furthermore, through systematic exploration of the ratio between different attention mechanisms in the hybrid architecture, we have identified the currently optimal model structure. Additionally, by leveraging our self-developed high-performance FP8 operator library-linghe, overall training efficiency has been improved by 50%. Benefiting from the high alignment between the training and inference engine operators, the models can undergo long-term, stable, and highly efficient optimization during the reinforcement learning phase, consistently maintaining SOTA performance across multiple challenging complex reasoning benchmarks.

Transformer models struggle with long-context inference due to their quadratic time and linear memory complexity. Recurrent Memory Transformers (RMTs) offer a solution by reducing the asymptotic cost to linear time and constant memory usage. However, their memory update mechanism leads to sequential execution, causing a performance bottleneck. We introduce Diagonal Batching, a scheduling scheme that unlocks parallelism across segments in RMTs while preserving exact recurrence. This approach eliminates the sequential constraint, enabling efficient GPU inference even for single long-context inputs without complex batching and pipelining techniques. Because the technique is purely a run-time computation reordering, existing RMT models adopt it with no retraining. Applied to a LLaMA-1B ARMT model, Diagonal Batching yields a 3.3x speedup over standard full-attention LLaMA-1B and a 1.8x speedup over the sequential RMT implementation on 131,072-token sequences. By removing sequential bottleneck, Diagonal Batching reduces inference cost and latency, thereby strengthening RMTs as a practical solution for real-world, long-context applications.

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key technique for enabling efficient LLM inference in industrial scenarios. While recent studies have focused on optimizing the memory occupied by the KV cache, they overlook two critical factors: preserving semantic coherence and considering task-specific characteristic during compression. To address these limitations, we propose a novel task-adaptive KV cache window selection method, WindowKV. WindowKV dynamically selects local semantic windows consisting of consecutive tokens, according to task-specific characteristics, ensuring the retained KV cache captures continuous, essential context. Additionally, we introduce an intra-group layer KV cache indices sharing strategy to reduce computational overhead, achieving a balance between performance and efficiency. We rigorously evaluate WindowKV on the LongBench benchmark, and the results demonstrate that it maintains a performance comparable to full KV cache retention while using only 12% of the original KV cache, significantly reducing memory requirements. Furthermore, our method also achieves state-of-the-art results in the Needle-in-a-Haystack evaluation, highlighting its effectiveness and robustness.

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM applications demand flexible and high-performance attention solutions. We present FlashInfer: a customizable and efficient attention engine for LLM serving. FlashInfer tackles KV-cache storage heterogeneity using block-sparse format and composable formats to optimize memory access and reduce redundancy. It also offers a customizable attention template, enabling adaptation to various settings through Just-In-Time (JIT) compilation. Additionally, FlashInfer's load-balanced scheduling algorithm adjusts to dynamism of user requests while maintaining compatibility with CUDAGraph which requires static configuration. FlashInfer have been integrated into leading LLM serving frameworks like SGLang, vLLM and MLC-Engine. Comprehensive kernel-level and end-to-end evaluations demonstrate FlashInfer's ability to significantly boost kernel performance across diverse inference scenarios: compared to state-of-the-art LLM serving solutions, FlashInfer achieve 29-69% inter-token-latency reduction compared to compiler backends for LLM serving benchmark, 28-30% latency reduction for long-context inference, and 13-17% speedup for LLM serving with parallel generation.

Large language models (LLMs) enable long-context tasks but face efficiency challenges due to the growing key-value (KV) cache. We propose LeanK, a learning-based method that prunes unimportant key (K) cache channels by leveraging static channel sparsity. With a novel two-stage training process, LeanK learns channel-wise static mask that could satisfy specific sparsity ratio and hardware alignment requirement. LeanK reduces GPU memory and accelerates decoding without sacrificing accuracy. Experiments demonstrate up to 70% K cache and 16%-18% V cache memory reduction. Custom decoding kernel enables 1.3x speedup for attention computation. We also provide insights into model channels and attention heads during long-context inference by analyzing the learned importance distribution. Our code is available at https://aka.ms/LeanK.

The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most previous efforts leveraged on the attention weight to evict non-critical cache tokens. But there is a trade-off in those methods, they usually require major modifiation of the inference infrastructure and significant computation overhead. Base on the fact that the Large Lanuage models are autoregresssive models, we propose {\it LagKV}, a KV allocation strategy only relying on straight forward comparison among KV themself. It is a totally attention free method which offers easy integration to the main stream inference platform and comparable performance comparing to other complicated KV compression methods. Results on LongBench and PasskeyRetrieval show that, our approach achieves nearly zero loss when the ratio is 2times and approx 90% of the original model performance for 8times. Especially in the 64-digit passkey retrieval task, our mehod outperforms the attention weight based method H_2O over 60% with same compression ratios. Our code is available at https://github.com/AI-Lab-China-Merchants-Bank/LagKV.

Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and efficient long-context inference. In these scenarios, the Key-Value (KV) cache is the primary bottleneck in terms of both GPU memory and latency, as the full KV cache must be loaded for each decoding step. While speculative decoding is a widely accepted technique to accelerate autoregressive decoding, existing methods often struggle to achieve significant speedups due to inefficient KV cache optimization strategies and result in low acceptance rates. To address these challenges, we propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration. QuantSpec maintains high acceptance rates (>90%) and reliably provides consistent end-to-end speedups upto sim2.5times, outperforming other self-speculative decoding methods that use sparse KV cache for long-context LLM inference. QuantSpec also reduces the memory requirements by sim 1.3times compared to these alternatives.

Long-Context Transformer Models (LCTMs) are vital for real-world applications but suffer high computational costs due to attention's quadratic complexity. Block-sparse attention mitigates this by focusing computation on critical regions, yet existing methods struggle with balancing accuracy and efficiency due to costly block importance measurements. In this paper, we introduce XAttention, a plug-and-play framework that dramatically accelerates long-context inference in Transformers models using sparse attention. XAttention's key innovation is the insight that the sum of antidiagonal values (i.e., from the lower-left to upper-right) in the attention matrix provides a powerful proxy for block importance. This allows for precise identification and pruning of non-essential blocks, resulting in high sparsity and dramatically accelerated inference. Across comprehensive evaluations on demanding long-context benchmarks-including RULER and LongBench for language, VideoMME for video understanding, and VBench for video generation. XAttention achieves accuracy comparable to full attention while delivering substantial computational gains. We demonstrate up to 13.5x acceleration in attention computation. These results underscore XAttention's ability to unlock the practical potential of block sparse attention, paving the way for scalable and efficient deployment of LCTMs in real-world applications. Code is available at https://github.com/mit-han-lab/x-attention.

Efficient long-sequence generation is a critical challenge for Large Language Models. While recent sparse decoding methods improve efficiency, they suffer from KV cache misalignment, where approximation errors accumulate and degrade generation quality. In this work, we propose Rectified Sparse Attention (ReSA), a simple yet effective method that combines block-sparse attention with periodic dense rectification. By refreshing the KV cache at fixed intervals using a dense forward pass, ReSA bounds error accumulation and preserves alignment with the pretraining distribution. Experiments across math reasoning, language modeling, and retrieval tasks demonstrate that ReSA achieves near-lossless generation quality with significantly improved efficiency. Notably, ReSA delivers up to 2.42times end-to-end speedup under decoding at 256K sequence length, making it a practical solution for scalable long-context inference. Code is available at https://aka.ms/ReSA-LM.

Recent advances in large language models (LLMs) have led to remarkable progress in natural language processing, but their computational and memory demands remain a significant challenge, particularly for long-context inference. We introduce TPTT (Transforming Pretrained Transformer into Titans), a novel framework for enhancing pretrained Transformer models with efficient linearized attention mechanisms and advanced memory management. TPTT employs techniques such as Memory as Gate (MaG) and mixed linearized attention (LiZA). It is fully compatible with the Hugging Face Transformers library, enabling seamless adaptation of any causal LLM through parameter-efficient fine-tuning (LoRA) without full retraining. We show the effectiveness of TPTT on the MMLU benchmark with models of approximately 1 billion parameters, observing substantial improvements in both efficiency and accuracy. For instance, Titans-Llama-3.2-1B achieves a 20% increase in Exact Match (EM) over its baseline. Statistical analyses and comparisons with recent state-of-the-art methods confirm the practical scalability and robustness of TPTT. Code is available at https://github.com/fabienfrfr/tptt . Python package at https://pypi.org/project/tptt/ .

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache compression methods either enforce rigid heuristics, disrupt tensor layouts with per-attention-head variability, or require specialized compute kernels. We propose a simple, yet effective, KV cache compression framework based on attention-guided, layer-adaptive composite tokens. Our method aggregates attention scores to estimate token importance, selects head-specific tokens independently, and aligns them into composite tokens that respect the uniform cache structure required by existing inference engines. A global allocation mechanism further adapts retention budgets across layers, assigning more capacity to layers with informative tokens. This approach achieves significant memory reduction while preserving accuracy, consistently outperforming prior structured and semi-structured methods. Crucially, our approach remains fully compatible with standard inference pipelines, offering a practical and scalable solution for efficient long-context LLM deployment.

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges. Existing approaches either discard potentially critical information needed for future generations or offer limited efficiency gains due to high computational overhead. In this paper, we introduce Chelsea, a simple yet effective framework for online KV cache clustering. Our approach is based on the observation that key states exhibit high similarity along the sequence dimension. To enable efficient clustering, we divide the sequence into chunks and propose Chunked Soft Matching, which employs an alternating partition strategy within each chunk and identifies clusters based on similarity. Chelsea then merges the KV cache within each cluster into a single centroid. Additionally, we provide a theoretical analysis of the computational complexity and the optimality of the intra-chunk partitioning strategy. Extensive experiments across various models and long-context benchmarks demonstrate that Chelsea achieves up to 80% reduction in KV cache memory usage while maintaining comparable model performance. Moreover, with minimal computational overhead, Chelsea accelerates the decoding stage of inference by up to 3.19times and reduces end-to-end latency by up to 2.72times.

Transformer-based large Language Models (LLMs) become increasingly important in various domains. However, the quadratic time complexity of attention operation poses a significant challenge for scaling to longer contexts due to the extremely high inference latency and GPU memory consumption for caching key-value (KV) vectors. This paper proposes RetrievalAttention, a training-free approach to accelerate attention computation. To leverage the dynamic sparse property of attention, RetrievalAttention builds approximate nearest neighbor search (ANNS) indexes upon KV vectors in CPU memory and retrieves the most relevant ones via vector search during generation. Due to the out-of-distribution (OOD) between query vectors and key vectors, off-the-shelf ANNS indexes still need to scan O(N) (usually 30% of all keys) data for accurate retrieval, which fails to exploit the high sparsity. RetrievalAttention first identifies the OOD challenge of ANNS-based attention, and addresses it via an attention-aware vector search algorithm that can adapt to queries and only access 1--3% of data, thus achieving a sub-linear time complexity. RetrievalAttention greatly reduces the inference cost of long-context LLM with much lower GPU memory requirements while maintaining the model accuracy. Especially, RetrievalAttention only needs 16GB GPU memory for serving 128K tokens in LLMs with 8B parameters, which is capable of generating one token in 0.188 seconds on a single NVIDIA RTX4090 (24GB).

The increasing context window size in Large Language Models (LLMs), such as the GPT and LLaMA series, has improved their ability to tackle complex, long-text tasks, but at the cost of inference efficiency, particularly regarding memory and computational complexity. Existing methods, including selective token retention and window-based attention, improve efficiency but risk discarding important tokens needed for future text generation. In this paper, we propose an approach that enhances LLM efficiency without token loss by reducing the memory and computational load of less important tokens, rather than discarding them.We address two challenges: 1) investigating the distribution of important tokens in the context, discovering recent tokens are more important than distant tokens in context, and 2) optimizing resources for distant tokens by sharing attention scores across layers. The experiments show that our method saves 35% KV cache without compromising the performance.

Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on resource-constrained edge devices poses significant challenges, including (1) intensive computations and huge model sizes, (2) great memory and bandwidth demands introduced by the autoregressive generation process, and (3) limited scalability for handling long sequences. To address these challenges, we propose AccLLM, a comprehensive acceleration framework that enables efficient and fast long-context LLM inference through algorithm and hardware co-design. At the algorithmic level, we integrate (1) pruning, (2) {\Lambda}-shaped attention, and (3) an innovative W2A8KV4 (2-bit weights, 8-bit activations, and 4-bit KV cache) quantization scheme, thus effectively reducing memory and bandwidth requirements while facilitating LLMs' long-sequence generation. At the hardware level, we design a dedicated FPGA-based accelerator with a reconfigurable computing engine to effectively and flexibly accommodate diverse operations arising from our compression algorithm, thereby fully translating the algorithmic innovations into tangible hardware efficiency. We validate AccLLM on the Xilinx Alveo U280 FPGA, demonstrating a 4.07x energy efficiency and a 2.98x throughput compared to the state-of-the-art work FlightLLM.

As large language models (LLMs) show impressive performance on complex tasks, they still struggle with longer contextual understanding and high computational costs. To balance efficiency and quality, we introduce LLMSteer, a fine-tuning-free framework that enhances LLMs through query-independent attention steering. Tested on popular LLMs and datasets, LLMSteer narrows the performance gap with baselines by 65.9% and reduces the runtime delay by up to 4.8x compared to recent attention steering methods.

The inference of transformer-based large language models consists of two sequential stages: 1) a prefilling stage to compute the KV cache of prompts and generate the first token, and 2) a decoding stage to generate subsequent tokens. For long prompts, the KV cache must be computed for all tokens during the prefilling stage, which can significantly increase the time needed to generate the first token. Consequently, the prefilling stage may become a bottleneck in the generation process. An open question remains whether all prompt tokens are essential for generating the first token. To answer this, we introduce a novel method, LazyLLM, that selectively computes the KV for tokens important for the next token prediction in both the prefilling and decoding stages. Contrary to static pruning approaches that prune the prompt at once, LazyLLM allows language models to dynamically select different subsets of tokens from the context in different generation steps, even though they might be pruned in previous steps. Extensive experiments on standard datasets across various tasks demonstrate that LazyLLM is a generic method that can be seamlessly integrated with existing language models to significantly accelerate the generation without fine-tuning. For instance, in the multi-document question-answering task, LazyLLM accelerates the prefilling stage of the LLama 2 7B model by 2.34x while maintaining accuracy.

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed decreases significantly as the sequence length grows. This slowdown is primarily caused by loading a large KV cache during self-attention. Previous works have shown that a small portion of critical tokens will dominate the attention outcomes. However, we observe the criticality of a token highly depends on the query. To this end, we propose Quest, a query-aware KV cache selection algorithm. Quest keeps track of the minimal and maximal Key values in KV cache pages and estimates the criticality of a given page using Query vectors. By only loading the Top-K critical KV cache pages for attention, Quest significantly speeds up self-attention without sacrificing accuracy. We show that Quest can achieve up to 2.23x self-attention speedup, which reduces inference latency by 7.03x while performing well on tasks with long dependencies with negligible accuracy loss. Code is available at http://github.com/mit-han-lab/Quest .

Advanced Large Language Models (LLMs) have achieved impressive performance across a wide range of complex and long-context natural language tasks. However, performing long-context LLM inference locally on a commodity GPU (a PC) with privacy concerns remains challenging due to the increasing memory demands of the key-value (KV) cache. Existing systems typically identify important tokens and selectively offload their KV data to GPU and CPU memory. The KV data needs to be offloaded to disk due to the limited memory on a commodity GPU, but the process is bottlenecked by token importance evaluation overhead and the disk's low bandwidth. In this paper, we present LeoAM, the first efficient importance-aware long-context LLM inference system for a single commodity GPU with adaptive hierarchical GPU-CPU-Disk KV management. Our system employs an adaptive KV management strategy that partitions KV data into variable-sized chunks based on the skewed distribution of attention weights across different layers to reduce computational and additional transmission overheads. Moreover, we propose a lightweight KV abstract method, which minimizes transmission latency by storing and extracting the KV abstract of each chunk on disk instead of the full KV data. LeoAM also leverages the dynamic compression and pipeline techniques to further accelerate inference. Experimental results demonstrate that LongInfer achieves an average inference latency speedup of 3.46x, while maintaining comparable LLM response quality. In scenarios with larger batch sizes, it achieves up to a 5.47x speedup.

The growing context lengths of large language models (LLMs) pose significant challenges for efficient inference, primarily due to GPU memory and bandwidth constraints. We present RetroInfer, a novel system that reconceptualizes the key-value (KV) cache as a vector storage system which exploits the inherent attention sparsity to accelerate long-context LLM inference. At its core is the wave index, an Attention-aWare VEctor index that enables efficient and accurate retrieval of critical tokens through techniques such as tripartite attention approximation, accuracy-bounded attention estimation, and segmented clustering. Complementing this is the wave buffer, which coordinates KV cache placement and overlaps computation and data transfer across GPU and CPU to sustain high throughput. Unlike prior sparsity-based methods that struggle with token selection and hardware coordination, RetroInfer delivers robust performance without compromising model accuracy. Experiments on long-context benchmarks show up to 4.5X speedup over full attention within GPU memory limits and up to 10.5X over sparse attention baselines when KV cache is extended to CPU memory, all while preserving full-attention-level accuracy.

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity require additional pretraining or finetuning, and often sacrifice model accuracy. In this paper, we first provide both theoretical and empirical foundations for near-lossless sparse attention. We find dynamically capturing head-specific sparse patterns at runtime with low overhead is crucial. To address this, we propose SampleAttention, an adaptive structured and near-lossless sparse attention. Leveraging observed significant sparse patterns, SampleAttention attends to a fixed percentage of adjacent tokens to capture local window patterns, and employs a two-stage query-guided key-value filtering approach, which adaptively select a minimum set of key-values with low overhead, to capture column stripe patterns. Comprehensive evaluations show that SampleAttention can seamlessly replace vanilla attention in off-the-shelf LLMs with nearly no accuracy loss, and reduces TTFT by up to 2.42times compared with FlashAttention.

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the increasing memory footprint and the need to access it for each token generation both result in low throughput when serving long-context LLMs. While various dynamic sparse attention methods have been proposed to speed up inference while maintaining generation quality, they either fail to sufficiently reduce GPU memory consumption or introduce significant decoding latency by offloading the KV cache to the CPU. We present ShadowKV, a high-throughput long-context LLM inference system that stores the low-rank key cache and offloads the value cache to reduce the memory footprint for larger batch sizes and longer sequences. To minimize decoding latency, ShadowKV employs an accurate KV selection strategy that reconstructs minimal sparse KV pairs on-the-fly. By evaluating ShadowKV on a broad range of benchmarks, including RULER, LongBench, and Needle In A Haystack, and models like Llama-3.1-8B, Llama-3-8B-1M, GLM-4-9B-1M, Yi-9B-200K, Phi-3-Mini-128K, and Qwen2-7B-128K, we demonstrate that it can support up to 6times larger batch sizes and boost throughput by up to 3.04times on an A100 GPU without sacrificing accuracy, even surpassing the performance achievable with infinite batch size under the assumption of infinite GPU memory. The code is available at https://github.com/bytedance/ShadowKV.

Recent advances in large language models (LLMs) have showcased exceptional performance in long-context tasks, while facing significant inference efficiency challenges with limited GPU memory. Existing solutions first proposed the sliding-window approach to accumulate a set of historical key-value (KV) pairs for reuse, then further improvements selectively retain its subsets at each step. However, due to the sparse attention distribution across a long context, it is hard to identify and recall relevant KV pairs, as the attention is distracted by massive candidate pairs. Additionally, we found it promising to select representative tokens as probe-Query in each sliding window to effectively represent the entire context, which is an approach overlooked by existing methods. Thus, we propose ActQKV, a training-free, Activation-aware approach that dynamically determines probe-Query and leverages it to retrieve the relevant KV pairs for inference. Specifically, ActQKV monitors a token-level indicator, Activation Bias, within each context window, enabling the proper construction of probe-Query for retrieval at pre-filling stage. To accurately recall the relevant KV pairs and minimize the irrelevant ones, we design a dynamic KV cut-off mechanism guided by information density across layers at the decoding stage. Experiments on the Long-Bench and infty Benchmarks demonstrate its state-of-the-art performance with competitive inference quality and resource efficiency.

In this work, we demonstrate that distinctive keys during LLM inference tend to have high attention scores. We explore this phenomenon and propose KeyDiff, a training-free KV cache eviction method based on key similarity. This method facilitates the deployment of LLM-based application requiring long input prompts in resource-constrained environments with limited memory and compute budgets. Unlike other KV cache eviction methods, KeyDiff can process arbitrarily long prompts within strict resource constraints and efficiently generate responses. We demonstrate that KeyDiff computes the optimal solution to a KV cache selection problem that maximizes key diversity, providing a theoretical understanding of KeyDiff. Notably,KeyDiff does not rely on attention scores, allowing the use of optimized attention mechanisms like FlashAttention. We demonstrate the effectiveness of KeyDiff across diverse tasks and models, illustrating a performance gap of less than 0.04\% with 8K cache budget (sim 23\% KV cache reduction) from the non-evicting baseline on the LongBench benchmark for Llama 3.1-8B and Llama 3.2-3B.

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache, which imposes a huge burden on the GPU VRAM, especially for resource-constraint scenarios (e.g., edge computing and personal devices). Several cost-effective solutions leverage host memory or SSDs to reduce storage costs for offline inference scenarios and improve the throughput. Nevertheless, they suffer from significant performance penalties imposed by intensive KV cache accesses due to limited PCIe bandwidth. To address these issues, we propose InstInfer, a novel LLM inference system that offloads the most performance-critical computation (i.e., attention in decoding phase) and data (i.e., KV cache) parts to Computational Storage Drives (CSDs), which minimize the enormous KV transfer overheads. InstInfer designs a dedicated flash-aware in-storage attention engine with KV cache management mechanisms to exploit the high internal bandwidths of CSDs instead of being limited by the PCIe bandwidth. The optimized P2P transmission between GPU and CSDs further reduces data migration overheads. Experimental results demonstrate that for a 13B model using an NVIDIA A6000 GPU, InstInfer improves throughput for long-sequence inference by up to 11.1times, compared to existing SSD-based solutions such as FlexGen.

We introduce Long-VITA, a simple yet effective large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M tokens while delivering advanced performances on short-context multi-modal tasks. We propose an effective multi-modal training schema that starts with large language models and proceeds through vision-language alignment, general knowledge learning, and two sequential stages of long-sequence fine-tuning. We further implement context-parallelism distributed inference and logits-masked language modeling head to scale Long-VITA to infinitely long inputs of images and texts during model inference. Regarding training data, Long-VITA is built on a mix of 17M samples from public datasets only and demonstrates the state-of-the-art performance on various multi-modal benchmarks, compared against recent cutting-edge models with internal data. Long-VITA is fully reproducible and supports both NPU and GPU platforms for training and testing. By leveraging our inference designs, Long-VITA models achieve a remarkable 2x prefill speedup and 4x context length extension in single node with 8 GPUs. We hope Long-VITA can serve as a competitive baseline and offer valuable insights for the open-source community in advancing long-context multi-modal understanding.

Long context understanding remains challenging for large language models due to their limited context windows. This paper presents Long Input Fine-Tuning (LIFT), a novel framework for long-context modeling that can improve the long-context performance of arbitrary (short-context) LLMs by dynamically adapting model parameters based on the long input. Importantly, LIFT, rather than endlessly extending the context window size to accommodate increasingly longer inputs in context, chooses to store and absorb the long input in parameter. By fine-tuning the long input into model parameters, LIFT allows short-context LLMs to answer questions even when the required information is not provided in the context during inference. Furthermore, to enhance LIFT performance while maintaining the original in-context learning (ICL) capabilities, we introduce Gated Memory, a specialized attention adapter that automatically balances long input memorization and ICL. We provide a comprehensive analysis of the strengths and limitations of LIFT on long context understanding, offering valuable directions for future research.

Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector Quantization (CommVQ) to significantly reduce memory usage for long-context LLM inference. We first introduce additive quantization with a lightweight encoder and codebook to compress the KV cache, which can be decoded via simple matrix multiplication. To further reduce computational costs during decoding, we design the codebook to be commutative with Rotary Position Embedding (RoPE) and train it using an Expectation-Maximization (EM) algorithm. This enables efficient integration of decoding into the self-attention mechanism. Our approach achieves high accuracy with additive quantization and low overhead via the RoPE-commutative codebook. Experiments on long-context benchmarks and GSM8K show that our method reduces FP16 KV cache size by 87.5% with 2-bit quantization, while outperforming state-of-the-art KV cache quantization methods. Notably, it enables 1-bit KV cache quantization with minimal accuracy loss, allowing a LLaMA-3.1 8B model to run with a 128K context length on a single RTX 4090 GPU. The source code is available at: https://github.com/UMass-Embodied-AGI/CommVQ.

Large Language Models (LLMs) with long context windows enable powerful applications but come at the cost of high memory consumption to store the Key and Value states (KV-Cache). Recent studies attempted to merge KV-cache from multiple layers into shared representations, yet these approaches either require expensive pretraining or rely on assumptions of high per-token cosine similarity across layers which generally does not hold in practice. We find that the dominant singular vectors are remarkably well-aligned across multiple layers of the KV-Cache. Exploiting this insight, we propose xKV, a simple post-training method that applies Singular Value Decomposition (SVD) on the KV-Cache of grouped layers. xKV consolidates the KV-Cache of multiple layers into a shared low-rank subspace, significantly reducing KV-Cache sizes. Through extensive evaluations on the RULER long-context benchmark with widely-used LLMs (e.g., Llama-3.1 and Qwen2.5), xKV achieves up to 6.8x higher compression rates than state-of-the-art inter-layer technique while improving accuracy by 2.7%. Moreover, xKV is compatible with the emerging Multi-Head Latent Attention (MLA) (e.g., DeepSeek-Coder-V2), yielding a notable 3x compression rates on coding tasks without performance degradation. These results highlight xKV's strong capability and versatility in addressing memory bottlenecks for long-context LLM inference. Our code is publicly available at: https://github.com/abdelfattah-lab/xKV.

Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by training on long-context data, followed by architectural modifications to reduce the overhead of KV cache during serving. This paper argues that integrating length extension with a GPU-friendly KV cache reduction architecture not only reduces training overhead during length extension, but also achieves better long-context performance. This leads to our proposed LongGen, which finetunes a pretrained LLM into an efficient architecture during length extension. LongGen builds on three key insights: (1) Sparse attention patterns, such as window attention (attending to recent tokens), attention sink (initial ones), and blockwise sparse attention (strided token blocks) are well-suited for building efficient long-context models, primarily due to their GPU-friendly memory access patterns, enabling efficiency gains not just theoretically but in practice as well. (2) It is essential for the model to have direct access to all tokens. A hybrid architecture with 1/3 full attention layers and 2/3 efficient ones achieves a balanced trade-off between efficiency and long-context performance. (3) Lightweight training on 5B long-context data is sufficient to extend the hybrid model's context length from 4K to 128K. We evaluate LongGen on both Llama-2 7B and Llama-2 70B, demonstrating its effectiveness across different scales. During training with 128K-long contexts, LongGen achieves 1.55x training speedup and reduces wall-clock time by 36%, compared to a full-attention baseline. During inference, LongGen reduces KV cache memory by 62%, achieving 1.67x prefilling speedup and 1.41x decoding speedup.

Encoder-only transformer models such as BERT offer a great performance-size tradeoff for retrieval and classification tasks with respect to larger decoder-only models. Despite being the workhorse of numerous production pipelines, there have been limited Pareto improvements to BERT since its release. In this paper, we introduce ModernBERT, bringing modern model optimizations to encoder-only models and representing a major Pareto improvement over older encoders. Trained on 2 trillion tokens with a native 8192 sequence length, ModernBERT models exhibit state-of-the-art results on a large pool of evaluations encompassing diverse classification tasks and both single and multi-vector retrieval on different domains (including code). In addition to strong downstream performance, ModernBERT is also the most speed and memory efficient encoder and is designed for inference on common GPUs.

Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in memory and inference time, and potential context truncation when the input exceeds the LLM's fixed context length. This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact. We test our approach using common data sources requiring long context processing: arXiv papers, news articles, and long conversations, on tasks of summarisation, question answering, and response generation. Experimental results show that Selective Context significantly reduces memory cost and decreases generation latency while maintaining comparable performance compared to that achieved when full context is used. Specifically, we achieve a 50\% reduction in context cost, resulting in a 36\% reduction in inference memory usage and a 32\% reduction in inference time, while observing only a minor drop of .023 in BERTscore and .038 in faithfulness on four downstream applications, indicating that our method strikes a good balance between efficiency and performance.

Long-context capability is critical for multi-modal foundation models. We introduce LongVILA, a full-stack solution for long-context vision-language models, including system, model training, and dataset development. On the system side, we introduce the first Multi-Modal Sequence Parallelism (MM-SP) system that enables long-context training and inference, enabling 2M context length training on 256 GPUs. MM-SP is also efficient, being 2.1x - 5.7x faster than Ring-Style Sequence Parallelism and 1.1x - 1.4x faster than Megatron-LM in text-only settings. Moreover, it seamlessly integrates with Hugging Face Transformers. For model training, we propose a five-stage pipeline comprising alignment, pre-training, context extension, and long-short joint supervised fine-tuning. Regarding datasets, we meticulously construct large-scale visual language pre-training datasets and long video instruction-following datasets to support our multi-stage training process. The full-stack solution extends the feasible frame number of VILA by a factor of 128 (from 8 to 1024 frames) and improves long video captioning score from 2.00 to 3.26 (1.6x), achieving 99.5% accuracy in 1400-frames video (274k context length) needle in a haystack. LongVILA-8B also demonstrates a consistent improvement in performance on long videos within the VideoMME benchmark as the video frames increase.

Recent progress in sparse attention mechanisms has demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs). Native Sparse Attention (NSA), a state-of-the-art approach, introduces natively trainable, hardware-aligned sparse attention that delivers substantial system-level performance gains while maintaining accuracy comparable to full attention. However, the kernel implementation of NSA relies on a query-grouping strategy that is efficient only with large Grouped Query Attention (GQA) sizes, whereas modern LLMs typically adopt much smaller GQA groups, which limits the applicability of this sparse algorithmic advance. In this work, we propose Flash Sparse Attention (FSA), which includes an alternative kernel design that enables efficient NSA computation across a wide range of popular LLMs with varied smaller GQA group sizes on modern GPUs. Compared to vanilla NSA kernel implementation, our empirical evaluation demonstrates that FSA achieves (i) up to 3.5times and on average 1.6times kernel-level latency reduction, (ii) up to 1.25times and 1.09times on average end-to-end training speedup on state-of-the-art LLMs, and (iii) up to 1.36times and 1.11times on average end-to-end prefill speedup on state-of-the-art LLMs. The source code is open-sourced and publicly available at https://github.com/Relaxed-System-Lab/Flash-Sparse-Attention.

Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large models on non-NVIDIA platforms also poses challenges for stable and efficient training. To address this, we introduce SpikingBrain, a family of brain-inspired models designed for efficient long-context training and inference. SpikingBrain leverages the MetaX GPU cluster and focuses on three aspects: (1) Model Architecture: linear and hybrid-linear attention architectures with adaptive spiking neurons; (2) Algorithmic Optimizations: an efficient, conversion-based training pipeline and a dedicated spike coding framework; (3) System Engineering: customized training frameworks, operator libraries, and parallelism strategies tailored to MetaX hardware. Using these techniques, we develop two models: SpikingBrain-7B, a linear LLM, and SpikingBrain-76B, a hybrid-linear MoE LLM. These models demonstrate the feasibility of large-scale LLM development on non-NVIDIA platforms. SpikingBrain achieves performance comparable to open-source Transformer baselines while using only about 150B tokens for continual pre-training. Our models significantly improve long-sequence training efficiency and deliver inference with (partially) constant memory and event-driven spiking behavior. For example, SpikingBrain-7B attains over 100x speedup in Time to First Token for 4M-token sequences. Training remains stable for weeks on hundreds of MetaX C550 GPUs, with the 7B model reaching a Model FLOPs Utilization of 23.4 percent. The proposed spiking scheme achieves 69.15 percent sparsity, enabling low-power operation. Overall, this work demonstrates the potential of brain-inspired mechanisms to drive the next generation of efficient and scalable large model design.

Online temporal action localization (On-TAL) is the task of identifying multiple action instances given a streaming video. Since existing methods take as input only a video segment of fixed size per iteration, they are limited in considering long-term context and require tuning the segment size carefully. To overcome these limitations, we propose memory-augmented transformer (MATR). MATR utilizes the memory queue that selectively preserves the past segment features, allowing to leverage long-term context for inference. We also propose a novel action localization method that observes the current input segment to predict the end time of the ongoing action and accesses the memory queue to estimate the start time of the action. Our method outperformed existing methods on two datasets, THUMOS14 and MUSES, surpassing not only TAL methods in the online setting but also some offline TAL methods.

Long-context language models exhibit impressive performance but remain challenging to deploy due to high GPU memory demands during inference. We propose Memory-efficient Offloaded Mini-sequence Inference (MOM), a method that partitions critical layers into smaller "mini-sequences" and integrates seamlessly with KV cache offloading. Experiments on various Llama, Qwen, and Mistral models demonstrate that MOM reduces peak memory usage by over 50\% on average. On Meta-Llama-3.2-8B, MOM extends the maximum context length from 155k to 455k tokens on a single A100 80GB GPU, while keeping outputs identical and not compromising accuracy. MOM also maintains highly competitive throughput due to minimal computational overhead and efficient last-layer processing. Compared to traditional chunked prefill methods, MOM achieves a 35\% greater context length extension. More importantly, our method drastically reduces prefill memory consumption, eliminating it as the longstanding dominant memory bottleneck during inference. This breakthrough fundamentally changes research priorities, redirecting future efforts from prefill-stage optimizations to improving decode-stage residual KV cache efficiency.

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined masks, failing to capture heterogeneous attention patterns. This results in suboptimal token interactions, limiting adaptability and retrieval accuracy in long-sequence tasks. This work introduces a dynamic sparse attention mechanism that assigns adaptive masks at the attention-map level, preserving heterogeneous patterns across layers and heads. Unlike existing approaches, our method eliminates the need for fine-tuning and predefined mask structures while maintaining computational efficiency. By learning context-aware attention structures, it achieves high alignment with full-attention models, ensuring minimal performance degradation while reducing memory and compute overhead. This approach provides a scalable alternative to full attention, enabling the practical deployment of large-scale Large Language Models (LLMs) without sacrificing retrieval performance. DAM is available at: https://github.com/HanzhiZhang-Ulrica/DAM.

The scaling of inference computation has unlocked the potential of long-context large language models (LLMs) across diverse settings. For knowledge-intensive tasks, the increased compute is often allocated to incorporate more external knowledge. However, without effectively utilizing such knowledge, solely expanding context does not always enhance performance. In this work, we investigate inference scaling for retrieval augmented generation (RAG), exploring strategies beyond simply increasing the quantity of knowledge. We focus on two inference scaling strategies: in-context learning and iterative prompting. These strategies provide additional flexibility to scale test-time computation (e.g., by increasing retrieved documents or generation steps), thereby enhancing LLMs' ability to effectively acquire and utilize contextual information. We address two key questions: (1) How does RAG performance benefit from the scaling of inference computation when optimally configured? (2) Can we predict the optimal test-time compute allocation for a given budget by modeling the relationship between RAG performance and inference parameters? Our observations reveal that increasing inference computation leads to nearly linear gains in RAG performance when optimally allocated, a relationship we describe as the inference scaling laws for RAG. Building on this, we further develop the computation allocation model to estimate RAG performance across different inference configurations. The model predicts optimal inference parameters under various computation constraints, which align closely with the experimental results. By applying these optimal configurations, we demonstrate that scaling inference compute on long-context LLMs achieves up to 58.9% gains on benchmark datasets compared to standard RAG.

Generating long sequences of tokens given a long-context input imposes a heavy computational burden for large language models (LLMs). One of the computational bottleneck comes from computing attention over a long sequence of input at each generation step. In this paper, we propose Recycled Attention, an inference-time method which alternates between full context attention and attention over a subset of input tokens. When performing partial attention, we recycle the attention pattern of a previous token that has performed full attention and attend only to the top K most attended tokens, reducing the cost of data movement and attention computation. Compared to previously proposed inference-time acceleration method which attends only to local context or tokens with high accumulative attention scores, our approach flexibly chooses tokens that are relevant to the current decoding step. We evaluate our methods on RULER, a suite of tasks designed to comprehensively evaluate long-context abilities, and long-context language modeling tasks. Applying our method to off-the-shelf LLMs achieves comparable speedup to baselines which only consider local context while improving the performance by 2x. We further explore two ideas to improve performance-efficiency trade-offs: (1) dynamically decide when to perform recycled or full attention step based on the query similarities and (2) continued pre-training the model with Recycled Attention.

In this paper, we introduce Writing in the Margins (WiM), a new inference pattern for Large Language Models designed to optimize the handling of long input sequences in retrieval-oriented tasks. This approach leverages the chunked prefill of the key-value cache to perform segment-wise inference, which enables efficient processing of extensive contexts along with the generation and classification of intermediate information ("margins") that guide the model towards specific tasks. This method increases computational overhead marginally while significantly enhancing the performance of off-the-shelf models without the need for fine-tuning. Specifically, we observe that WiM provides an average enhancement of 7.5% in accuracy for reasoning skills (HotpotQA, MultiHop-RAG) and more than a 30.0% increase in the F1-score for aggregation tasks (CWE). Additionally, we show how the proposed pattern fits into an interactive retrieval design that provides end-users with ongoing updates about the progress of context processing, and pinpoints the integration of relevant information into the final response. We release our implementation of WiM using Hugging Face Transformers library at https://github.com/writer/writing-in-the-margins.

Answering complex, long-context questions remains a major challenge for large language models (LLMs) as it requires effective question clarifications and context retrieval. We propose Agentic Long-Context Understanding (AgenticLU), a framework designed to enhance an LLM's understanding of such queries by integrating targeted self-clarification with contextual grounding within an agentic workflow. At the core of AgenticLU is Chain-of-Clarifications (CoC), where models refine their understanding through self-generated clarification questions and corresponding contextual groundings. By scaling inference as a tree search where each node represents a CoC step, we achieve 97.8% answer recall on NarrativeQA with a search depth of up to three and a branching factor of eight. To amortize the high cost of this search process to training, we leverage the preference pairs for each step obtained by the CoC workflow and perform two-stage model finetuning: (1) supervised finetuning to learn effective decomposition strategies, and (2) direct preference optimization to enhance reasoning quality. This enables AgenticLU models to generate clarifications and retrieve relevant context effectively and efficiently in a single inference pass. Extensive experiments across seven long-context tasks demonstrate that AgenticLU significantly outperforms state-of-the-art prompting methods and specialized long-context LLMs, achieving robust multi-hop reasoning while sustaining consistent performance as context length grows.

A recent trend in LLMs is developing recurrent sub-quadratic models that improve long-context processing efficiency. We investigate leading large long-context models, focusing on how their fixed-size recurrent memory affects their performance. Our experiments reveal that, even when these models are trained for extended contexts, their use of long contexts remains underutilized. Specifically, we demonstrate that a chunk-based inference procedure, which identifies and processes only the most relevant portion of the input can mitigate recurrent memory failures and be effective for many long-context tasks: On LongBench, our method improves the overall performance of Falcon3-Mamba-Inst-7B by 14%, Falcon-Mamba-Inst-7B by 28%, RecurrentGemma-IT-9B by 50%, and RWKV6-Finch-7B by 51%. Surprisingly, this simple approach also leads to state-of-the-art results in the challenging LongBench v2 benchmark, showing competitive performance with equivalent size Transformers. Furthermore, our findings raise questions about whether recurrent models genuinely exploit long-range dependencies, as our single-chunk strategy delivers stronger performance - even in tasks that presumably require cross-context relations.

We present context parallelism for long-context large language model inference, which achieves near-linear scaling for long-context prefill latency with up to 128 H100 GPUs across 16 nodes. Particularly, our method achieves 1M context prefill with Llama3 405B model in 77s (93% parallelization efficiency, 63% FLOPS utilization) and 128K context prefill in 3.8s. We develop two lossless exact ring attention variants: pass-KV and pass-Q to cover a wide range of use cases with the state-of-the-art performance: full prefill, persistent KV prefill and decode. Benchmarks on H100 GPU hosts inter-connected with RDMA and TCP both show similar scalability for long-context prefill, demonstrating that our method scales well using common commercial data center with medium-to-low inter-host bandwidth.

Large language models are prominently used in real-world applications, often tasked with reasoning over large volumes of documents. An exciting development in this space is models boasting extended context capabilities, with some accommodating over 2 million tokens. Such long context model capabilities remain uncertain in production systems, motivating the need to benchmark their performance on real world use cases. We address this challenge by proposing SWiM, an evaluation framework that addresses the limitations of standard tests. Testing the framework on eight long context models, we find that even strong models such as GPT-4 and Claude 3 Opus degrade in performance when information is present in the middle of the context window (lost-in-the-middle effect). Next, in addition to our benchmark, we propose medoid voting, a simple, but effective training-free approach that helps alleviate this effect, by generating responses a few times, each time randomly permuting documents in the context, and selecting the medoid answer. We evaluate medoid voting on single document QA tasks, achieving up to a 24% lift in accuracy.

We present an approximate attention mechanism named HyperAttention to address the computational challenges posed by the growing complexity of long contexts used in Large Language Models (LLMs). Recent work suggests that in the worst-case scenario, quadratic time is necessary unless the entries of the attention matrix are bounded or the matrix has low stable rank. We introduce two parameters which measure: (1) the max column norm in the normalized attention matrix, and (2) the ratio of row norms in the unnormalized attention matrix after detecting and removing large entries. We use these fine-grained parameters to capture the hardness of the problem. Despite previous lower bounds, we are able to achieve a linear time sampling algorithm even when the matrix has unbounded entries or a large stable rank, provided the above parameters are small. HyperAttention features a modular design that easily accommodates integration of other fast low-level implementations, particularly FlashAttention. Empirically, employing Locality Sensitive Hashing (LSH) to identify large entries, HyperAttention outperforms existing methods, giving significant speed improvements compared to state-of-the-art solutions like FlashAttention. We validate the empirical performance of HyperAttention on a variety of different long-context length datasets. For example, HyperAttention makes the inference time of ChatGLM2 50\% faster on 32k context length while perplexity increases from 5.6 to 6.3. On larger context length, e.g., 131k, with causal masking, HyperAttention offers 5-fold speedup on a single attention layer.

Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond. However, simply extending the input sequence length does not necessarily lead to effective long-context understanding. In this study, we integrate Chain-of-Thought (CoT) reasoning into LLMs in a supervised manner to facilitate effective long-context understanding. To achieve this, we introduce LongFinanceQA, a synthetic dataset in the financial domain designed to improve long-context reasoning. Unlike existing long-context synthetic data, LongFinanceQA includes intermediate CoT reasoning before the final conclusion, which encourages LLMs to perform explicit reasoning, improving accuracy and interpretability in long-context understanding. To generate synthetic CoT reasoning, we propose Property-driven Agentic Inference (PAI), an agentic framework that simulates human-like reasoning steps, including property extraction, retrieval, and summarization. We evaluate PAI's reasoning capabilities by assessing GPT-4o-mini w/ PAI on the Loong benchmark, outperforming standard GPT-4o-mini by 20.0%. Furthermore, we fine-tune LLaMA-3.1-8B-Instruct on LongFinanceQA, achieving a 24.6% gain on Loong's financial subset.

Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models support contexts of 100K-1M tokens, this setup is costly to serve because the memory consumption of the KV cache scales with input length. We explore an alternative: training a smaller KV cache offline on each corpus. At inference time, we load this trained KV cache, which we call a Cartridge, and decode a response. Critically, the cost of training a Cartridge can be amortized across all the queries referencing the same corpus. However, we find that the naive approach of training the Cartridge with next-token prediction on the corpus is not competitive with ICL. Instead, we propose self-study, a training recipe in which we generate synthetic conversations about the corpus and train the Cartridge with a context-distillation objective. We find that Cartridges trained with self-study replicate the functionality of ICL, while being significantly cheaper to serve. On challenging long-context benchmarks, Cartridges trained with self-study match ICL performance while using 38.6x less memory and enabling 26.4x higher throughput. Self-study also extends the model's effective context length (e.g. from 128k to 484k tokens on MTOB) and surprisingly, leads to Cartridges that can be composed at inference time without retraining.

Video diffusion models have recently shown promise for world modeling through autoregressive frame prediction conditioned on actions. However, they struggle to maintain long-term memory due to the high computational cost associated with processing extended sequences in attention layers. To overcome this limitation, we propose a novel architecture leveraging state-space models (SSMs) to extend temporal memory without compromising computational efficiency. Unlike previous approaches that retrofit SSMs for non-causal vision tasks, our method fully exploits the inherent advantages of SSMs in causal sequence modeling. Central to our design is a block-wise SSM scanning scheme, which strategically trades off spatial consistency for extended temporal memory, combined with dense local attention to ensure coherence between consecutive frames. We evaluate the long-term memory capabilities of our model through spatial retrieval and reasoning tasks over extended horizons. Experiments on Memory Maze and Minecraft datasets demonstrate that our approach surpasses baselines in preserving long-range memory, while maintaining practical inference speeds suitable for interactive applications.

This paper tackles the memory hurdle of processing long context sequences in Large Language Models (LLMs), by presenting a novel approach, Dropping In Convolutions for Long Context Compression (LoCoCo). LoCoCo employs only a fixed-size Key-Value (KV) cache, and can enhance efficiency in both inference and fine-tuning stages. Diverging from prior methods that selectively drop KV pairs based on heuristics, LoCoCo leverages a data-driven adaptive fusion technique, blending previous KV pairs with incoming tokens to minimize the loss of contextual information and ensure accurate attention modeling. This token integration is achieved through injecting one-dimensional convolutional kernels that dynamically calculate mixing weights for each KV cache slot. Designed for broad compatibility with existing LLM frameworks, LoCoCo allows for straightforward "drop-in" integration without needing architectural modifications, while incurring minimal tuning overhead. Experiments demonstrate that LoCoCo maintains consistently outstanding performance across various context lengths and can achieve a high context compression rate during both inference and fine-tuning phases. During inference, we successfully compressed up to 3482 tokens into a 128-size KV cache, while retaining comparable performance to the full sequence - an accuracy improvement of up to 0.2791 compared to baselines at the same cache size. During post-training tuning, we also effectively extended the context length from 4K to 32K using a KV cache of fixed size 512, achieving performance similar to fine-tuning with entire sequences.

Long-context capabilities are essential for a wide range of applications, including document and video understanding, in-context learning, and inference-time scaling, all of which require models to process and reason over long sequences of text and multimodal data. In this work, we introduce a efficient training recipe for building ultra-long context LLMs from aligned instruct model, pushing the boundaries of context lengths from 128K to 1M, 2M, and 4M tokens. Our approach leverages efficient continued pretraining strategies to extend the context window and employs effective instruction tuning to maintain the instruction-following and reasoning abilities. Our UltraLong-8B, built on Llama3.1-Instruct with our recipe, achieves state-of-the-art performance across a diverse set of long-context benchmarks. Importantly, models trained with our approach maintain competitive performance on standard benchmarks, demonstrating balanced improvements for both long and short context tasks. We further provide an in-depth analysis of key design choices, highlighting the impacts of scaling strategies and data composition. Our findings establish a robust framework for efficiently scaling context lengths while preserving general model capabilities. We release all model weights at: https://ultralong.github.io/.

Large Language models (LLMs) have become a research hotspot. To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique. However, as the inference length increases, growing KV caches might lead to out-of-memory issues. Many existing methods address this issue through KV cache compression, primarily by preserving key tokens throughout all layers to reduce information loss. Most of them allocate a uniform budget size for each layer to retain. However, we observe that the minimum budget sizes needed to retain essential information vary across layers and models based on the perspectives of attention and hidden state output. Building on this observation, this paper proposes a simple yet effective KV cache compression method that leverages layer uncertainty to allocate budget size for each layer. Experimental results show that the proposed method can reduce memory usage of the KV caches to only sim20\% when compared to Full KV inference while achieving nearly lossless performance.

Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency. Our research introduces a novel approach for the long context bottleneck to accelerate LLM inference and reduce GPU memory consumption. Our research demonstrates that LLMs can identify relevant tokens in the early layers before generating answers to a query. Leveraging this insight, we propose an algorithm that uses early layers of an LLM as filters to select and compress input tokens, significantly reducing the context length for subsequent processing. Our method, GemFilter, demonstrates substantial improvements in both speed and memory efficiency compared to existing techniques, such as standard attention and SnapKV/H2O. Notably, it achieves a 2.4times speedup and 30\% reduction in GPU memory usage compared to SOTA methods. Evaluation on the Needle in a Haystack task shows that GemFilter significantly outperforms standard attention, SnapKV and demonstrates comparable performance on the LongBench challenge. GemFilter is simple, training-free, and broadly applicable across different LLMs. Crucially, it provides interpretability by allowing humans to inspect the selected input sequence. These findings not only offer practical benefits for LLM deployment, but also enhance our understanding of LLM internal mechanisms, paving the way for further optimizations in LLM design and inference. Our code is available at https://github.com/SalesforceAIResearch/GemFilter.

Large Language Models (LLMs) have become more prevalent in long-context applications such as interactive chatbots, document analysis, and agent workflows, but it is challenging to serve long-context requests with low latency and high throughput. Speculative decoding (SD) is a widely used technique to reduce latency without sacrificing performance but the conventional wisdom suggests that its efficacy is limited to small batch sizes. In MagicDec, we show that surprisingly SD can achieve speedup even for a high throughput inference regime for moderate to long sequences. More interestingly, an intelligent drafting strategy can achieve better speedup with increasing batch size based on our rigorous analysis. MagicDec first identifies the bottleneck shifts with increasing batch size and sequence length, and uses these insights to deploy speculative decoding more effectively for high throughput inference. Then, it leverages draft models with sparse KV cache to address the KV bottleneck that scales with both sequence length and batch size.

A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. However, RNNs are fundamentally unable to randomly access historical context, and simply integrating attention mechanisms may undermine their efficiency advantages. To overcome this limitation, we propose Hierarchical Sparse Attention (HSA), a novel attention mechanism that enhances RNNs with long-range random access flexibility while preserving their merits in efficiency and length generalization. HSA divides inputs into chunks, selecting the top-k chunks and hierarchically aggregates information. The core innovation lies in learning token-to-chunk relevance based on fine-grained token-level information inside each chunk. This approach enhances the precision of chunk selection across both in-domain and out-of-domain context lengths. To make HSA efficient, we further introduce a hardware-aligned kernel design. By combining HSA with Mamba, we introduce RAMba, which achieves perfect accuracy in passkey retrieval across 64 million contexts despite pre-training on only 4K-length contexts, and significant improvements on various downstream tasks, with nearly constant memory footprint. These results show RAMba's huge potential in long-context modeling.

Retrieval-augmented generation (RAG) and long-context language models (LCLMs) both address context limitations of LLMs in open-domain question answering (QA). However, optimal external context to retrieve remains an open problem: fixing the retrieval size risks either wasting tokens or omitting key evidence. Existing adaptive methods like Self-RAG and Self-Route rely on iterative LLM prompting and perform well on factoid QA, but struggle with aggregation QA, where the optimal context size is both unknown and variable. We present Adaptive-k retrieval, a simple and effective single-pass method that adaptively selects the number of passages based on the distribution of the similarity scores between the query and the candidate passages. It does not require model fine-tuning, extra LLM inferences or changes to existing retriever-reader pipelines. On both factoid and aggregation QA benchmarks, Adaptive-k matches or outperforms fixed-k baselines while using up to 10x fewer tokens than full-context input, yet still retrieves 70% of relevant passages. It improves accuracy across five LCLMs and two embedding models, highlighting that dynamically adjusting context size leads to more efficient and accurate QA.

Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some cases, directly all necessary information. However, simply feeding more documents into the context window fails to capture how evidence should be connected. We address this gap with thought templates, which recast reasoning as reusable thought caches, derived from prior problem solving traces, structuring how evidence is combined and guiding multi-hop inference with factual documents. To keep these templates effective, we propose an update strategy that iteratively refines templates derived from training data through natural-language feedback. Across diverse benchmarks and LCLM families, our approach delivers consistent gains over strong baselines in both retrieval-based and retrieval-free settings. Furthermore, we show that optimized templates can be distilled into smaller open-source models, demonstrating its broad applicability and transparent reasoning reuse. We refer to our framework as Thought Template Augmented LCLMs (ToTAL).

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention computation, it takes 30 minutes for an 8B LLM to process a prompt of 1M tokens (i.e., the pre-filling stage) on a single A100 GPU. Existing methods for speeding up prefilling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs. To address this gap, we introduce MInference (Milliontokens Inference), a sparse calculation method designed to accelerate pre-filling of long-sequence processing. Specifically, we identify three unique patterns in long-context attention matrices-the A-shape, Vertical-Slash, and Block-Sparsethat can be leveraged for efficient sparse computation on GPUs. We determine the optimal pattern for each attention head offline and dynamically build sparse indices based on the assigned pattern during inference. With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs. Our proposed technique can be directly applied to existing LLMs without any modifications to the pre-training setup or additional fine-tuning. By evaluating on a wide range of downstream tasks, including InfiniteBench, RULER, PG-19, and Needle In A Haystack, and models including LLaMA-3-1M, GLM4-1M, Yi-200K, Phi-3-128K, and Qwen2-128K, we demonstrate that MInference effectively reduces inference latency by up to 10x for pre-filling on an A100, while maintaining accuracy. Our code is available at https://aka.ms/MInference.

While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. To mitigate this issue, we propose Sequential Chunk-wise Optimization (SeCO), a memory-efficient training paradigm that partitions lengthy inputs into manageable chunks. Each chunk independently constructs its computational graph and performs localized backpropagation, ensuring that only one chunk's forward activations are stored in memory. Building on SeCO, we further introduce Sparse Chunk-wise Optimization (SpaCO), which reduces computational overhead by selectively propagating gradients to specific chunks and incorporates a carefully designed compensation factor to ensure unbiased gradient estimation. SpaCO decouples the computational cost of backpropagation from the context length, enabling training time to gradually converge to inference time as sequences become longer. Implemented as lightweight training wrappers, both SeCO and SpaCO offer substantial practical benefits. For example, when fine-tuning an 8B model with LoRA on a single RTX 3090 GPU, SeCO expands maximum sequence length from 1K to 16K tokens, while SpaCO demonstrates accelerated training speed -- achieving up to 3x faster than SeCO under the same experimental setup. These innovations provide new insights into optimizing long-context models, making them more accessible for practical applications. We have open-sourced the code at https://github.com/wenhaoli-xmu/seco{here}.

Long Context Language Models (LCLMs) have emerged as a new paradigm to perform Information Retrieval (IR), which enables the direct ingestion and retrieval of information by processing an entire corpus in their single context, showcasing the potential to surpass traditional sparse and dense retrieval methods. However, processing a large number of passages within in-context for retrieval is computationally expensive, and handling their representations during inference further exacerbates the processing time; thus, we aim to make LCLM retrieval more efficient and potentially more effective with passage compression. Specifically, we propose a new compression approach tailored for LCLM retrieval, which is trained to maximize the retrieval performance while minimizing the length of the compressed passages. To accomplish this, we generate the synthetic data, where compressed passages are automatically created and labeled as chosen or rejected according to their retrieval success for a given query, and we train the proposed Compression model for Long context Retrieval (CoLoR) with this data via preference optimization while adding the length regularization loss on top of it to enforce brevity. Through extensive experiments on 9 datasets, we show that CoLoR improves the retrieval performance by 6% while compressing the in-context size by a factor of 1.91. Our code is available at: https://github.com/going-doer/CoLoR.

We present systematic efforts in building long-context multilingual text representation model (TRM) and reranker from scratch for text retrieval. We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pre-trained in a native 8192-token context (longer than 512 of previous multilingual encoders). Then we construct a hybrid TRM and a cross-encoder reranker by contrastive learning. Evaluations show that our text encoder outperforms the same-sized previous state-of-the-art XLM-R. Meanwhile, our TRM and reranker match the performance of large-sized state-of-the-art BGE-M3 models and achieve better results on long-context retrieval benchmarks. Further analysis demonstrate that our proposed models exhibit higher efficiency during both training and inference. We believe their efficiency and effectiveness could benefit various researches and industrial applications.

We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources. For example, training on the context length of 8192 needs 16x computational costs in self-attention layers as that of 2048. In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shift short attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. Particularly, it can be implemented with only two lines of code in training, while being optional in inference. On the other hand, we revisit the parameter-efficient fine-tuning regime for context expansion. Notably, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA demonstrates strong empirical results on various tasks on LLaMA2 models from 7B/13B to 70B. LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like FlashAttention-2. In addition, to make LongLoRA practical, we collect a dataset, LongQA, for supervised fine-tuning. It contains more than 3k long context question-answer pairs.

Long-sequence modeling faces a fundamental trade-off between the efficiency of compressive fixed-size memory in RNN-like models and the fidelity of lossless growing memory in attention-based Transformers. Inspired by the Multi-Store Model in cognitive science, we introduce a memory framework of artificial neural networks. Our method maintains a sliding window of the Transformer's KV cache as lossless short-term memory, while a learnable module termed Artificial Hippocampus Network (AHN) recurrently compresses out-of-window information into a fixed-size compact long-term memory. To validate this framework, we instantiate AHNs using modern RNN-like architectures, including Mamba2, DeltaNet, and Gated DeltaNet. Extensive experiments on long-context benchmarks LV-Eval and InfiniteBench demonstrate that AHN-augmented models consistently outperform sliding window baselines and achieve performance comparable or even superior to full-attention models, while substantially reducing computational and memory requirements. For instance, augmenting the Qwen2.5-3B-Instruct with AHNs reduces inference FLOPs by 40.5% and memory cache by 74.0%, while improving its average score on LV-Eval (128k sequence length) from 4.41 to 5.88. Code is available at: https://github.com/ByteDance-Seed/AHN.

Large Language Models (LLMs) have shown exciting performance in listwise passage ranking. Due to the limited input length, existing methods often adopt the sliding window strategy. Such a strategy, though effective, is inefficient as it involves repetitive and serialized processing, which usually re-evaluates relevant passages multiple times. As a result, it incurs redundant API costs, which are proportional to the number of inference tokens. The development of long-context LLMs enables the full ranking of all passages within a single inference, avoiding redundant API costs. In this paper, we conduct a comprehensive study of long-context LLMs for ranking tasks in terms of efficiency and effectiveness. Surprisingly, our experiments reveal that full ranking with long-context LLMs can deliver superior performance in the supervised fine-tuning setting with a huge efficiency improvement. Furthermore, we identify two limitations of fine-tuning the full ranking model based on existing methods: (1) sliding window strategy fails to produce a full ranking list as a training label, and (2) the language modeling loss cannot emphasize top-ranked passage IDs in the label. To alleviate these issues, we propose a new complete listwise label construction approach and a novel importance-aware learning objective for full ranking. Experiments show the superior performance of our method over baselines. Our codes are available at https://github.com/8421BCD/fullrank.

Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deployment. While various compression strategies have been explored, sequence-level compression, which drops the full KV caches for certain tokens, is particularly challenging as it can lead to the loss of important contextual information. To address this, we introduce UniGist, a sequence-level long-context compression framework that efficiently preserves context information by replacing raw tokens with special compression tokens (gists) in a fine-grained manner. We adopt a chunk-free training strategy and design an efficient kernel with a gist shift trick, enabling optimized GPU training. Our scheme also supports flexible inference by allowing the actual removal of compressed tokens, resulting in real-time memory savings. Experiments across multiple long-context tasks demonstrate that UniGist significantly improves compression quality, with especially strong performance in detail-recalling tasks and long-range dependency modeling.

Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient plug-and-play refiner that leverages the inherent structural characteristics of long documents. LongRefiner employs dual-level query analysis, hierarchical document structuring, and adaptive refinement through multi-task learning on a single foundation model. Experiments on seven QA datasets demonstrate that LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to the best baseline. Further analysis validates that LongRefiner is scalable, efficient, and effective, providing practical insights for real-world long-text RAG applications. Our code is available at https://github.com/ignorejjj/LongRefiner.

Long Context Understanding (LCU) is a critical area for exploration in current large language models (LLMs). However, due to the inherently lengthy nature of long-text data, existing LCU benchmarks for LLMs often result in prohibitively high evaluation costs, like testing time and inference expenses. Through extensive experimentation, we discover that existing LCU benchmarks exhibit significant redundancy, which means the inefficiency in evaluation. In this paper, we propose a concise data compression method tailored for long-text data with sparse information characteristics. By pruning the well-known LCU benchmark LongBench, we create MiniLongBench. This benchmark includes only 237 test samples across six major task categories and 21 distinct tasks. Through empirical analysis of over 60 LLMs, MiniLongBench achieves an average evaluation cost reduced to only 4.5% of the original while maintaining an average rank correlation coefficient of 0.97 with LongBench results. Therefore, our MiniLongBench, as a low-cost benchmark, holds great potential to substantially drive future research into the LCU capabilities of LLMs. See https://github.com/MilkThink-Lab/MiniLongBench for our code, data and tutorial.

Large language models (LLMs) have demonstrated remarkable progress in understanding long-context inputs. However, benchmarks for evaluating the long-context reasoning abilities of LLMs fall behind the pace. Existing benchmarks often focus on a narrow range of tasks or those that do not demand complex reasoning. To address this gap and enable a more comprehensive evaluation of the long-context reasoning capabilities of current LLMs, we propose a new synthetic benchmark, LongReason, which is constructed by synthesizing long-context reasoning questions from a varied set of short-context reasoning questions through context expansion. LongReason consists of 794 multiple-choice reasoning questions with diverse reasoning patterns across three task categories: reading comprehension, logical inference, and mathematical word problems. We evaluate 21 LLMs on LongReason, revealing that most models experience significant performance drops as context length increases. Our further analysis shows that even state-of-the-art LLMs still have significant room for improvement in providing robust reasoning across different tasks. We will open-source LongReason to support the comprehensive evaluation of LLMs' long-context reasoning capabilities.

Managing long texts is challenging for large language models (LLMs) due to limited context window sizes. This study introduces UIO-LLMs, an unbiased incremental optimization approach for memory-enhanced transformers under long-context settings. We initially conceptualize the process as a streamlined encoder-decoder framework where the weights-shared encoder and decoder respectively encapsulate a context segment into memories and leverage these memories to predict outputs of the subsequent segment. Subsequently, by treating our memory-enhanced transformers as fully-connected recurrent neural networks (RNNs), we refine the training process using the Truncated Backpropagation Through Time (TBPTT) algorithm, which incorporates innovative incremental optimization techniques. These techniques not only diminish time complexity but also address the bias in gradient computation through an unbiased optimization process. UIO-LLMs successfully handle long context, such as extending the context window of Llama2-7b-chat from 4K to 100K tokens with minimal 2% additional parameters, while keeping the inference cost nearly linear as context length increases.

Transformer-based long context generative models power emerging AI applications like hour-long video understanding and project-level coding agent. Deploying long context transformers (e.g., 100K to 10M tokens) is prohibitively expensive compared to short context (e.g., 4K tokens) model variants. Reducing the cost of long-context transformers is becoming a pressing research and engineering challenge starting from the year of 2024. This work describes a concurrent programming framework for quantitatively analyzing the efficiency challenges in serving multiple long-context requests under limited size of GPU high-bandwidth memory (HBM) regime. We give a detailed analysis of how all additional computational costs, compared to 4K context, trace back to one single source: the large size of the KV cache. We use a 34B GPT-3.5 level model of 50K context on A100 NVLink as a running example, and describe how its large KV cache causes four types of deployment challenges: (1) prefilling long inputs takes much longer compute time and GPU memory than short inputs; (2) after prefilling, the large KV cache residing on the GPU HBM substantially restricts the number of concurrent users being served; (3) during decoding, repeatedly reading the KV cache from HBM to SM largely increases latency; (4) when KV cache memory overflows, swapping it from HBM to DDR causes significant context switching latency. We use this framework to analyze existing works and identify possibilities of combining them to build end-to-end systems. Overall, this work offers a foundational framework for analyzing long context transformer deployment and identifies directions towards reducing the inference cost of 1M context to be as cheap as 4K.

Efficient processing of long contexts has been a persistent pursuit in Natural Language Processing. With the growing number of long documents, dialogues, and other textual data, it is important to develop Long Context Language Models (LCLMs) that can process and analyze extensive inputs in an effective and efficient way. In this paper, we present a comprehensive survey on recent advances in long-context modeling for large language models. Our survey is structured around three key aspects: how to obtain effective and efficient LCLMs, how to train and deploy LCLMs efficiently, and how to evaluate and analyze LCLMs comprehensively. For the first aspect, we discuss data strategies, architectural designs, and workflow approaches oriented with long context processing. For the second aspect, we provide a detailed examination of the infrastructure required for LCLM training and inference. For the third aspect, we present evaluation paradigms for long-context comprehension and long-form generation, as well as behavioral analysis and mechanism interpretability of LCLMs. Beyond these three key aspects, we thoroughly explore the diverse application scenarios where existing LCLMs have been deployed and outline promising future development directions. This survey provides an up-to-date review of the literature on long-context LLMs, which we wish to serve as a valuable resource for both researchers and engineers. An associated GitHub repository collecting the latest papers and repos is available at: https://github.com/LCLM-Horizon/A-Comprehensive-Survey-For-Long-Context-Language-Modeling{\color[RGB]{175,36,67}{LCLM-Horizon}}.

With the bomb ignited by ChatGPT, Transformer-based Large Language Models (LLMs) have paved a revolutionary path toward Artificial General Intelligence (AGI) and have been applied in diverse areas as knowledge bases, human interfaces, and dynamic agents. However, a prevailing limitation exists: many current LLMs, constrained by resources, are primarily pre-trained on shorter texts, rendering them less effective for longer-context prompts, commonly encountered in real-world settings. In this paper, we present a comprehensive survey focusing on the advancement of model architecture in Transformer-based LLMs to optimize long-context capabilities across all stages from pre-training to inference. We firstly delineate and analyze the problems of handling long-context input and output with the current Transformer-based models. Then, we mainly offer a holistic taxonomy to navigate the landscape of Transformer upgrades on architecture to solve these problems. Afterward, we provide the investigation on wildly used evaluation necessities tailored for long-context LLMs, including datasets, metrics, and baseline models, as well as some amazing optimization toolkits like libraries, systems, and compilers to augment LLMs' efficiency and efficacy across different stages. Finally, we further discuss the predominant challenges and potential avenues for future research in this domain. Additionally, we have established a repository where we curate relevant literature with real-time updates at https://github.com/Strivin0311/long-llms-learning.

This paper introduces LongBench v2, a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks. LongBench v2 consists of 503 challenging multiple-choice questions, with contexts ranging from 8k to 2M words, across six major task categories: single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repository understanding, and long structured data understanding. To ensure the breadth and the practicality, we collect data from nearly 100 highly educated individuals with diverse professional backgrounds. We employ both automated and manual review processes to maintain high quality and difficulty, resulting in human experts achieving only 53.7% accuracy under a 15-minute time constraint. Our evaluation reveals that the best-performing model, when directly answers the questions, achieves only 50.1% accuracy. In contrast, the o1-preview model, which includes longer reasoning, achieves 57.7%, surpassing the human baseline by 4%. These results highlight the importance of enhanced reasoning ability and scaling inference-time compute to tackle the long-context challenges in LongBench v2. The project is available at https://longbench2.github.io.

The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexity during the pre-filling phase remains a significant obstacle to real-world deployment. To overcome this limitation, we introduce MMInference (Multimodality Million tokens Inference), a dynamic sparse attention method that accelerates the prefilling stage for long-context multi-modal inputs. First, our analysis reveals that the temporal and spatial locality of video input leads to a unique sparse pattern, the Grid pattern. Simultaneously, VLMs exhibit markedly different sparse distributions across different modalities. We introduce a permutation-based method to leverage the unique Grid pattern and handle modality boundary issues. By offline search the optimal sparse patterns for each head, MMInference constructs the sparse distribution dynamically based on the input. We also provide optimized GPU kernels for efficient sparse computations. Notably, MMInference integrates seamlessly into existing VLM pipelines without any model modifications or fine-tuning. Experiments on multi-modal benchmarks-including Video QA, Captioning, VisionNIAH, and Mixed-Modality NIAH-with state-of-the-art long-context VLMs (LongVila, LlavaVideo, VideoChat-Flash, Qwen2.5-VL) show that MMInference accelerates the pre-filling stage by up to 8.3x at 1M tokens while maintaining accuracy. Our code is available at https://aka.ms/MMInference.

Long-context modeling presents a significant challenge for transformer-based large language models (LLMs) due to the quadratic complexity of the self-attention mechanism and issues with length extrapolation caused by pretraining exclusively on short inputs. Existing methods address computational complexity through techniques such as text chunking, the kernel approach, and structured attention, and tackle length extrapolation problems through positional encoding, continued pretraining, and data engineering. These approaches typically require sequential access to the document, necessitating reading from the first to the last token. We contend that for goal-oriented reading of long documents, such sequential access is not necessary, and a proficiently trained model can learn to omit hundreds of less pertinent tokens. Inspired by human reading behaviors and existing empirical observations, we propose random access, a novel reading strategy that enables transformers to efficiently process long documents without examining every token. Experimental results from pretraining, fine-tuning, and inference phases validate the efficacy of our method.

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and linear-increasing key-value memory footprint. To reduce computational costs and memory, key-value cache compression techniques are commonly applied at inference time, but this often leads to severe performance degradation, as models are not trained to handle compressed context. Although there are more sophisticated compression methods, they are typically unsuitable for post-training because of their incompatibility with gradient-based optimization or high computation overhead. To fill this gap with no additional parameter and little computation overhead, we propose Lag-Relative Sparse Attention(LRSA) anchored by the LagKV compression method for long context post-training. Our method performs chunk-by-chunk prefilling, which selects the top K most relevant key-value pairs in a fixed-size lagging window, allowing the model to focus on salient historical context while maintaining efficiency. Experimental results show that our approach significantly enhances the robustness of the LLM with key-value compression and achieves better fine-tuned results in the question-answer tuning task.

Complex, temporally evolving phenomena, from climate to brain activity, are governed by dynamical systems (DS). DS reconstruction (DSR) seeks to infer generative surrogate models of these from observed data, reproducing their long-term behavior. Existing DSR approaches require purpose-training for any new system observed, lacking the zero-shot and in-context inference capabilities known from LLMs. Here we introduce DynaMix, a novel multivariate ALRNN-based mixture-of-experts architecture pre-trained for DSR, the first DSR model able to generalize zero-shot to out-of-domain DS. Just from a provided context signal, without any re-training, DynaMix faithfully forecasts the long-term evolution of novel DS where existing time series (TS) foundation models, like Chronos, fail -- at a fraction of the number of parameters and orders of magnitude faster inference times. DynaMix outperforms TS foundation models in terms of long-term statistics, and often also short-term forecasts, even on real-world time series, like traffic or weather data, typically used for training and evaluating TS models, but not at all part of DynaMix' training corpus. We illustrate some of the failure modes of TS models for DSR problems, and conclude that models built on DS principles may bear a huge potential also for advancing the TS prediction field.

Recent years have seen the rapid development of large generative models for text; however, much less research has explored the connection between text and another "language" of communication -- music. Music, much like text, can convey emotions, stories, and ideas, and has its own unique structure and syntax. In our work, we bridge text and music via a text-to-music generation model that is highly efficient, expressive, and can handle long-term structure. Specifically, we develop Mo\^usai, a cascading two-stage latent diffusion model that can generate multiple minutes of high-quality stereo music at 48kHz from textual descriptions. Moreover, our model features high efficiency, which enables real-time inference on a single consumer GPU with a reasonable speed. Through experiments and property analyses, we show our model's competence over a variety of criteria compared with existing music generation models. Lastly, to promote the open-source culture, we provide a collection of open-source libraries with the hope of facilitating future work in the field. We open-source the following: Codes: https://github.com/archinetai/audio-diffusion-pytorch; music samples for this paper: http://bit.ly/44ozWDH; all music samples for all models: https://bit.ly/audio-diffusion.

Limited by the context window size of Large Language Models(LLMs), handling various tasks with input tokens exceeding the upper limit has been challenging, whether it is a simple direct retrieval task or a complex multi-hop reasoning task. Although various methods have been proposed to enhance the long-context processing capabilities of LLMs, they either incur substantial post-training costs, or require additional tool modules(e.g.,RAG), or have not shown significant improvement in realistic tasks. Our work observes the correlation between the attention distribution and generated answers across each layer, and establishes the attention allocation aligns with retrieval-augmented capabilities through experiments. Drawing on the above insights, we propose a novel method InfiniRetri that leverages the LLMs's own attention information to enable accurate retrieval across inputs of infinitely length. Our evaluations indicate that InfiniRetri achieves 100% accuracy in the Needle-In-a-Haystack(NIH) test over 1M tokens using a 0.5B parameter model, surpassing other method or larger models and setting a new state-of-the-art(SOTA). Moreover, our method achieves significant performance improvements on real-world benchmarks, with a maximum 288% improvement. In addition, InfiniRetri can be applied to any Transformer-based LLMs without additional training and substantially reduces inference latency and compute overhead in long texts. In summary, our comprehensive studies show InfiniRetri's potential for practical applications and creates a paradigm for retrievaling information using LLMs own capabilities under infinite-length tokens. Code will be released in link.

Processing long-form audio is a major challenge for Large Audio Language models (LALMs). These models struggle with the quadratic cost of attention (O(N^2)) and with modeling long-range temporal dependencies. Existing audio benchmarks are built mostly from short clips and do not evaluate models in realistic long context settings. To address this gap, we introduce AudioMarathon, a benchmark designed to evaluate both understanding and inference efficiency on long-form audio. AudioMarathon provides a diverse set of tasks built upon three pillars: long-context audio inputs with durations ranging from 90.0 to 300.0 seconds, which correspond to encoded sequences of 2,250 to 7,500 audio tokens, respectively, full domain coverage across speech, sound, and music, and complex reasoning that requires multi-hop inference. We evaluate state-of-the-art LALMs and observe clear performance drops as audio length grows. We also study acceleration techniques and analyze the trade-offs of token pruning and KV cache eviction. The results show large gaps across current LALMs and highlight the need for better temporal reasoning and memory-efficient architectures. We believe AudioMarathon will drive the audio and multimodal research community to develop more advanced audio understanding models capable of solving complex audio tasks.

Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As sequence lengths increase, the number of Key-Value (KV) pairs in LLMs escalates, creating a significant efficiency bottleneck. In this paper, we propose a new KV cache optimization paradigm called LaCache, a training-free method for efficient and accurate generative inference of LLMs. LaCache enables LLMs to simultaneously address both of the critical challenges in long-range modeling: robust long-range capabilities and continuous generation without running out-of-memory (OOM). Specifically, LaCache integrates two key innovations: (1) a ladder-shaped KV cache pattern that stores KV pairs not only sequentially (left-to-right within each layer) but also across layers (from shallow to deep), providing an extended span for capturing long-range dependencies under a fixed storage budget, thereby boosting long-range capabilities; and (2) an iterative compaction mechanism that progressively compresses older caches, freeing up space for new tokens within a fixed cache size. This token distance-based dynamic compression enables more effective continuous generation under constrained cache budgets. Experiments across various tasks, benchmarks, and LLM models consistently validate LaCache's effectiveness in enhancing LLMs' long-range capabilities. Our code is available at https://github.com/GATECH-EIC/LaCache.

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to efficient long-context processing show promise, recurrent compression-based methods struggle with information preservation, whereas random access approaches require substantial memory resources. We introduce REFORM, a novel inference framework that efficiently handles long contexts through a two-phase approach. First, it incrementally processes input chunks while maintaining a compressed KV cache, constructs cross-layer context embeddings, and utilizes early exit strategy for improved efficiency. Second, it identifies and gathers essential tokens via similarity matching and selectively recomputes the KV cache. Compared to baselines, REFORM achieves over 50% and 27% performance gains on RULER and BABILong respectively at 1M context length. It also outperforms baselines on Infinite-Bench and MM-NIAH, demonstrating flexibility across diverse tasks and domains. Additionally, REFORM reduces inference time by 30% and peak memory usage by 5%, achieving both efficiency and superior performance.

Building effective and efficient Transformer-based large language models (LLMs) has recently become a research focus, requiring maximizing model language capabilities and minimizing training and deployment costs. Existing efforts have primarily described complex relationships among model performance, parameter size, and data size, as well as searched for the optimal compute allocation to train LLMs. However, they overlook the impacts of context length and attention head configuration (the number of query and key-value heads in grouped-query attention) on training and inference. In this paper, we systematically compare models with different parameter sizes, context lengths, and attention head configurations in terms of model performance, computational cost, and memory cost. Then, we extend the existing scaling methods, which are based solely on parameter size and training compute, to guide the construction of cost-optimal LLMs during both training and inference. Our quantitative scaling studies show that, when processing sufficiently long sequences, a larger model with fewer attention heads can achieve a lower loss while incurring lower computational and memory costs. Our findings provide valuable insights for developing practical LLMs, especially in long-context processing scenarios. We will publicly release our code and data.

Large Language Models (LLMs) rely on attention mechanisms whose time complexity grows quadratically with input sequence length, creating significant computational bottlenecks during the prefilling stage. Existing static sparse attention methods typically degrade accuracy, while dynamic sparsity methods introduce additional computational overhead due to runtime sparse index estimation. To address these limitations, we propose TriangleMix, a novel training-free static attention pattern. TriangleMix employs dense attention in shallow layers and switches to a triangle-shaped sparse pattern in deeper layers. Extensive experiments demonstrate that TriangleMix reduces attention overhead by 3.7x to 15.3x in deep layers, and decreases overall Time-to-First-Token (TTFT) by 12% to 32% for sequence lengths ranging from 32K to 128K, without sacrificing model accuracy. Moreover, TriangleMix can be seamlessly integrated with dynamic sparsity methods to achieve further speedup, e.g. accelerating MInference by 19% at 128K, highlighting its potential to enhance LLM inference efficiency.

The linear growth of key-value (KV) cache memory and quadratic computational complexity pose significant bottlenecks for large language models (LLMs) in long-context processing. While existing KV cache optimization methods address these challenges through token pruning or feature merging, they often suffer from irreversible information loss or require costly parameter retraining. We propose ZeroMerge, a dynamic zero-shot compression framework that achieves efficient cache management through three key innovations: (1) Fine-grained memory allocation guided by multi-dimensional token importance metrics at head-level granularity, (2) A residual merging mechanism that preserves critical context through compensated attention scoring, and (3) Parameter-free adaptation compatible with diverse LLM architectures without retraining. Comprehensive evaluations across LLaMA-2 model demonstrate that ZeroMerge maintains full-cache performance at 5\% compression ratios while doubling inference throughput at 40K token lengths. The method effectively balances memory efficiency, generation quality, and deployment flexibility, advancing practical long-context LLM applications. The code is available at https://github.com/SusCom-Lab/ZeroMerge.

Extending the functionality of the Transformer model to accommodate longer sequence lengths has become a critical challenge. This extension is crucial not only for improving tasks such as language translation and long-context processing but also for enabling novel applications like chatbots, code generation, and multimedia content creation. The primary obstacle is the self-attention mechanism, which scales quadratically with sequence length in terms of computation time and memory requirements. LongLoRA proposed shifted sparse attention (S\(^2\)-Attn), effectively enabling context extension and leading to non-trivial computation savings with similar performance to fine-tuning with vanilla attention. However, LongLoRA is still not as efficient as vanilla attention, reaching only 39\% of the perplexity improvement compared to full attention. This inefficiency is due to the cyclic shift applied within different attention head patterns, causing either chaos in the attention head structure or unnecessary information exchange between token groups. To address these issues, We propose SinkLoRA, which features better work partitioning. Specifically, (1) we developed SF-Attn with a segmentation and reassembly algorithm to proportionally return cyclically shifted groups of attention heads to their un-shifted state together with global attention of "sink attention tokens", achieving 92\% of the perplexity improvement compared to full attention after fine tuning, and (2) applied a SOTA KV cache compression algorithm H_2O to accelerate inference. Furthermore, We conducted supervised fine-tuning with SinkLoRA using a self collected LongAlpaca-plus dataset. All our code, models, datasets, and demos are available at https://github.com/Dexter-GT-86/SinkLoRA.

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire growing sequence. Existing sparse attention methods reduce computation by pruning the key-value (KV) cache, yet they suffer from severe accuracy degradation on reasoning tasks due to cumulative selection errors and the dynamic importance of tokens over long derivations. We present DELTA, a training-free sparse attention mechanism that achieves computational efficiency without sacrificing model accuracy. DELTA partitions transformer layers into three groups: initial layers that use full attention, a small set of selection layers that identify salient tokens via aggregated head-level attention scores, and subsequent sparse-attention layers that attend only to the selected subset. This design preserves the full KV cache in GPU memory for accuracy, while avoiding expensive full-attention computation over many layers. On reasoning benchmarks such as AIME and GPQA-Diamond, DELTA matches or surpasses full attention in accuracy, while reducing the number of attended tokens by up to 5times and delivering 1.5times end-to-end speedup. Our results show that selective reuse of intermediate attention maps offers a robust path toward efficient long-context reasoning.

Many advanced Large Language Model (LLM) applications require long-context processing, but the self-attention module becomes a bottleneck during the prefilling stage of inference due to its quadratic time complexity with respect to sequence length. Existing sparse attention methods accelerate attention computation by skipping less significant regions of the attention map. However, these approaches typically perform coarse-grained inspection of the attention map, rendering considerable loss in model accuracy. In this paper, we propose SALE, a fine-grained sparse attention method that accelerates the long-context prefilling stage of LLM with negligible loss in model accuracy. SALE achieves fast and accurate fine-grained attention weight estimation through 4-bit quantized query-key products, followed by block-sparse attention to accelerate prefilling computations. For importance evaluation for query-key pairs, we adopt our Relative Attention Score metric, which offers significantly higher efficiency within our framework. We implement a custom CUDA kernel optimized for our approach for hardware efficiency, reducing the additional overhead to approximately 11% of the full attention latency. Notably, SALE requires no parameter training and can be seamlessly integrated into existing systems with trivial code modifications. Experiments on long-context benchmarks demonstrate that our method outperforms existing approaches in accuracy-efficiency trade-offs, achieving at least 3.36x speedups on Llama-3.1-8B for sequences longer than 64K while maintaining model quality.

While Mixture of Experts (MoE) models achieve remarkable efficiency by activating only subsets of parameters, they suffer from high memory access costs during inference. Memory-layer architectures offer an appealing alternative with very few memory access, but previous attempts like UltraMem have only matched the performance of 2-expert MoE models, falling significantly short of state-of-the-art 8-expert configurations. We present UltraMemV2, a redesigned memory-layer architecture that closes this performance gap. Our approach introduces five key improvements: integrating memory layers into every transformer block, simplifying value expansion with single linear projections, adopting FFN-based value processing from PEER, implementing principled parameter initialization, and rebalancing memory-to-FFN computation ratios. Through extensive evaluation, we demonstrate that UltraMemV2 achieves performance parity with 8-expert MoE models under same computation and parameters but significantly low memory access. Notably, UltraMemV2 shows superior performance on memory-intensive tasks, with improvements of +1.6 points on long-context memorization, +6.2 points on multi-round memorization, and +7.9 points on in-context learning. We validate our approach at scale with models up to 2.5B activated parameters from 120B total parameters, and establish that activation density has greater impact on performance than total sparse parameter count. Our work brings memory-layer architectures to performance parity with state-of-the-art MoE models, presenting a compelling alternative for efficient sparse computation.

Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input. While this ability significantly enhances MLLM capabilities, it introduces substantial computational challenges, primarily due to the quadratic complexity of self-attention mechanisms with numerous input tokens. To mitigate these bottlenecks, token compression has emerged as an auspicious and critical approach, efficiently reducing the number of tokens during both training and inference. In this paper, we present the first systematic survey and synthesis of the burgeoning field of multimodal long context token compression. Recognizing that effective compression strategies are deeply tied to the unique characteristics and redundancies of each modality, we categorize existing approaches by their primary data focus, enabling researchers to quickly access and learn methods tailored to their specific area of interest: (1) image-centric compression, which addresses spatial redundancy in visual data; (2) video-centric compression, which tackles spatio-temporal redundancy in dynamic sequences; and (3) audio-centric compression, which handles temporal and spectral redundancy in acoustic signals. Beyond this modality-driven categorization, we further dissect methods based on their underlying mechanisms, including transformation-based, similarity-based, attention-based, and query-based approaches. By providing a comprehensive and structured overview, this survey aims to consolidate current progress, identify key challenges, and inspire future research directions in this rapidly evolving domain. We also maintain a public repository to continuously track and update the latest advances in this promising area.

One essential advantage of recurrent neural networks (RNNs) over transformer-based language models is their linear computational complexity concerning the sequence length, which makes them much faster in handling long sequences during inference. However, most publicly available RNNs (e.g., Mamba and RWKV) are trained on sequences with less than 10K tokens, and their effectiveness in longer contexts remains largely unsatisfying so far. In this paper, we study the cause of the inability to process long context for RNNs and suggest critical mitigations. We examine two practical concerns when applying state-of-the-art RNNs to long contexts: (1) the inability to extrapolate to inputs longer than the training length and (2) the upper bound of memory capacity. Addressing the first concern, we first investigate *state collapse* (SC), a phenomenon that causes severe performance degradation on sequence lengths not encountered during training. With controlled experiments, we attribute this to overfitting due to the recurrent state being overparameterized for the training length. For the second concern, we train a series of Mamba-2 models on long documents to empirically estimate the recurrent state capacity in language modeling and passkey retrieval. Then, three SC mitigation methods are proposed to improve Mamba-2's length generalizability, allowing the model to process more than 1M tokens without SC. We also find that the recurrent state capacity in passkey retrieval scales exponentially to the state size, and we empirically train a Mamba-2 370M with near-perfect passkey retrieval accuracy on 256K context length. This suggests a promising future for RNN-based long-context modeling.

We present a decoder-only Transformer architecture that robustly generalizes to sequence lengths substantially longer than those seen during training. Our model, SWAN-GPT, interleaves layers without positional encodings (NoPE) and sliding-window attention layers equipped with rotary positional encodings (SWA-RoPE). Experiments demonstrate strong performance on sequence lengths significantly longer than the training length without the need for additional long-context training. This robust length extrapolation is achieved through our novel architecture, enhanced by a straightforward dynamic scaling of attention scores during inference. In addition, SWAN-GPT is more computationally efficient than standard GPT architectures, resulting in cheaper training and higher throughput. Further, we demonstrate that existing pre-trained decoder-only models can be efficiently converted to the SWAN architecture with minimal continued training, enabling longer contexts. Overall, our work presents an effective approach for scaling language models to longer contexts in a robust and efficient manner.

Efficient KV cache management in LLMs is crucial for long-context tasks like RAG and summarization. Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics and reducing the retention of essential information. However, we observe distinct activation patterns across layers in various tasks, highlighting the need for adaptive strategies tailored to each task's unique demands. Based on this insight, we propose DynamicKV, a method that dynamically optimizes token retention by adjusting the number of tokens retained at each layer to adapt to the specific task. DynamicKV establishes global and per-layer maximum KV cache budgets, temporarily retaining the maximum budget for the current layer, and periodically updating the KV cache sizes of all preceding layers during inference. Our method retains only 1.7% of the KV cache size while achieving ~85% of the Full KV cache performance on LongBench. Notably, even under extreme compression (0.9%), DynamicKV surpasses state-of-the-art (SOTA) methods by 11% in the Needle-in-a-Haystack test using Mistral-7B-Instruct-v0.2. The code will be released.

Optimizing inference for long-context Large Language Models (LLMs) is increasingly important due to the quadratic compute and linear memory complexity of Transformers. Existing approximation methods, such as key-value (KV) cache dropping, sparse attention, and prompt compression, typically rely on rough predictions of token or KV pair importance. We propose a novel framework for approximate LLM inference that leverages small draft models to more accurately predict the importance of tokens and KV pairs. Specifically, we introduce two instantiations of our proposed framework: (i) SpecKV, which leverages a draft output to accurately assess the importance of each KV pair for more effective KV cache dropping, and (ii) SpecPC, which uses the draft model's attention activations to identify and discard unimportant prompt tokens. To the best of our knowledge, this is the first work to use draft models for approximate LLM inference acceleration, extending their utility beyond traditional lossless speculative decoding. We motivate our methods with theoretical and empirical analyses, and show a strong correlation between the attention patterns of draft and target models. Extensive experiments on long-context benchmarks show that our methods consistently achieve higher accuracy than existing baselines, while preserving the same improvements in memory usage, latency, and throughput. Our code is available at https://github.com/furiosa-ai/draft-based-approx-llm.

In modern large language models (LLMs), handling very long context lengths presents significant challenges as it causes slower inference speeds and increased memory costs. Additionally, most existing pre-trained LLMs fail to generalize beyond their original training sequence lengths. To enable efficient and practical long-context utilization, we introduce InfiniteHiP, a novel, and practical LLM inference framework that accelerates processing by dynamically eliminating irrelevant context tokens through a modular hierarchical token pruning algorithm. Our method also allows generalization to longer sequences by selectively applying various RoPE adjustment methods according to the internal attention patterns within LLMs. Furthermore, we offload the key-value cache to host memory during inference, significantly reducing GPU memory pressure. As a result, InfiniteHiP enables the processing of up to 3 million tokens on a single L40s 48GB GPU -- 3x larger -- without any permanent loss of context information. Our framework achieves an 18.95x speedup in attention decoding for a 1 million token context without requiring additional training. We implement our method in the SGLang framework and demonstrate its effectiveness and practicality through extensive evaluations.

Transformer-based large language models (LLMs) demonstrate impressive performance in long context generation. Extending the context length has disproportionately shifted the memory footprint of LLMs during inference to the key-value cache (KV cache). In this paper, we propose HEADINFER, which offloads the KV cache to CPU RAM while avoiding the need to fully store the KV cache for any transformer layer on the GPU. HEADINFER employs a fine-grained, head-wise offloading strategy, maintaining only selective attention heads KV cache on the GPU while computing attention output dynamically. Through roofline analysis, we demonstrate that HEADINFER maintains computational efficiency while significantly reducing memory footprint. We evaluate HEADINFER on the Llama-3-8B model with a 1-million-token sequence, reducing the GPU memory footprint of the KV cache from 128 GB to 1 GB and the total GPU memory usage from 207 GB to 17 GB, achieving a 92% reduction compared to BF16 baseline inference. Notably, HEADINFER enables 4-million-token inference with an 8B model on a single consumer GPU with 24GB memory (e.g., NVIDIA RTX 4090) without approximation methods.

Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and memory challenges, which hinder their ability to provide efficient and responsive interactions. Most current acceleration methods either compress the context or optimize key value caching, but they often rely on fixed or position-based heuristics that do not adapt well to the dynamic and unpredictable patterns found in actual multi-turn conversations. In this paper, we present LoopServe, an adaptive dual-phase inference acceleration framework for large language models in multi-turn dialogues. LoopServe introduces two main innovations. First, it performs online sparsification during the prefilling phase by dynamically selecting the most important parts of the attention matrix for each new input. Second, it uses progressive key value compression during decoding by adaptively maintaining a relevant and efficient cache based on the most recently generated output tokens. We also propose a https://huggingface.co/datasets/TreeAILab/Multi-turn_Long-context_Benchmark_for_LLMs{new benchmark} with eleven multi-turn datasets that reflect realistic query positions and conversational dependencies. Extensive experiments demonstrate that LoopServe consistently achieves superior effectiveness compared to existing baselines and significantly accelerates LLM inference across a wide range of long-context dialogue tasks.

We propose the In-context Autoencoder (ICAE) for context compression in a large language model (LLM). The ICAE has two modules: a learnable encoder adapted with LoRA from an LLM for compressing a long context into a limited number of memory slots, and a fixed decoder which is the target LLM that can condition on the memory slots for various purposes. We first pretrain the ICAE using both autoencoding and language modeling objectives on massive text data, enabling it to generate memory slots that accurately and comprehensively represent the original context. Then, we fine-tune the pretrained ICAE on a small amount of instruct data to enhance its interaction with various prompts for producing desirable responses. Our experimental results demonstrate that the ICAE learned with our proposed pretraining and fine-tuning paradigm can effectively produce memory slots with 4times context compression, which can be well conditioned on by the target LLM to respond to various prompts. The promising results demonstrate significant implications of the ICAE for its novel approach to the long context problem and its potential to reduce computation and memory overheads for LLM inference in practice, suggesting further research effort in context management for an LLM. Our code and data will be released shortly.

Empowering LLMs with the ability to utilize useful information from a long context is crucial for many downstream applications. However, achieving long context lengths with the conventional transformer architecture requires substantial training and inference resources. In this paper, we present FocusLLM, a framework designed to extend the context length of any decoder-only LLM, enabling the model to focus on relevant information from very long sequences. FocusLLM processes long text inputs by dividing them into chunks based on the model's original context length to alleviate the issue of attention distraction. Then, it appends the local context to each chunk as a prompt to extract essential information from each chunk based on a novel parallel decoding mechanism, and ultimately integrates the extracted information into the local context. FocusLLM stands out for great training efficiency and versatility: trained with an 8K input length with much less training cost than previous methods, FocusLLM exhibits superior performance across downstream long-context tasks and maintains strong language modeling ability when handling extensive long texts, even up to 400K tokens. Our code is available at https://github.com/leezythu/FocusLLM.

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which constitutes the majority of the computational workload, primarily entails vector-matrix multiplications and interactions with the Key-Value (KV) Cache. This phase is constrained by memory bandwidth due to the overhead of transferring weights and KV cache values from the memory system to the computing units. This memory bottleneck becomes particularly pronounced in applications that require long-context and extensive text generation, both of which are increasingly crucial for LLMs. This paper introduces "Keyformer", an innovative inference-time approach, to mitigate the challenges associated with KV cache size and memory bandwidth utilization. Keyformer leverages the observation that approximately 90% of the attention weight in generative inference focuses on a specific subset of tokens, referred to as "key" tokens. Keyformer retains only the key tokens in the KV cache by identifying these crucial tokens using a novel score function. This approach effectively reduces both the KV cache size and memory bandwidth usage without compromising model accuracy. We evaluate Keyformer's performance across three foundational models: GPT-J, Cerebras-GPT, and MPT, which employ various positional embedding algorithms. Our assessment encompasses a variety of tasks, with a particular emphasis on summarization and conversation tasks involving extended contexts. Keyformer's reduction of KV cache reduces inference latency by 2.1x and improves token generation throughput by 2.4x, while preserving the model's accuracy.

Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose a novel approach to address this problem by learning contexts offline through context compression and in-domain parameter-efficient finetuning. Our method enables an LLM to create a concise representation of the original context and efficiently retrieve relevant information to answer questions accurately. We introduce LLoCO, a technique that combines context compression, retrieval, and parameter-efficient finetuning using LoRA. Our approach extends the effective context window of a 4k token LLaMA2-7B model to handle up to 128k tokens. We evaluate our approach on several long-context question-answering datasets, demonstrating that LLoCO significantly outperforms in-context learning while using 30times fewer tokens during inference. LLoCO achieves up to 7.62times speed-up and substantially reduces the cost of long document question answering, making it a promising solution for efficient long context processing. Our code is publicly available at https://github.com/jeffreysijuntan/lloco.

Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks. However, LLMs with long context windows have been notorious for their expensive training costs and high inference latency. Even the most advanced models such as GPT-4 and Claude2 often make mistakes when processing inputs of over 100k tokens, a phenomenon also known as lost in the middle. In this paper, we propose LongAgent, a method based on multi-agent collaboration, which scales LLMs (e.g., LLaMA) to a context of 128K and demonstrates potential superiority in long-text processing compared to GPT-4. In LongAgent, a leader is responsible for understanding user intent and directing team members to acquire information from documents. Due to members' hallucinations, it is non-trivial for a leader to obtain accurate information from the responses of dozens to hundreds of members. To address this, we develop an inter-member communication mechanism to resolve response conflicts caused by hallucinations through information sharing. Our experimental results indicate that LongAgent offers a promising alternative for long-text processing. The agent team instantiated with LLaMA-7B achieves significant improvements in tasks such as 128k-long text retrieval, multi-hop question answering, compared to GPT-4.

The KV-Cache technique has become the standard for the inference of large language models (LLMs). It caches states of self-attention to avoid recomputation. Yet, it is widely criticized that KV-Cache can become a bottleneck of the LLM inference system, especially when confronted with ultra-large models and long-context queries. A natural remedy is to discard the KV-Cache for less important tokens, with StreamingLLM as an example, but the used static eviction strategies cannot flexibly adapt to varying contexts. Remedies like H2O leverage accumulative attention scores to perform dynamic eviction but suffer from the attention bias issue in capturing contextual information. This paper bridges this gap by devising a parameterized KV-Cache eviction mechanism, dubbed as Attention-Gate, which accepts the whole context as input and yields eviction flags for each token to realize in-context eviction. The subsequent self-attention module proceeds according to the flags and only the KV states for the remaining tokens need to be cached. The Attention-Gates can vary among different heads and layers and be trivially plugged into pre-trained LLMs, tuned by cost-effective continual pre-training or supervised fine-tuning objectives to acquire what to discard. The computational and memory overhead introduced by Attention-Gates is minimal. Our method is validated across multiple tasks, demonstrating both efficiency and adaptability. After a highly efficient continual pre-training, it achieves higher average accuracy and evicts more tokens compared to traditional training-free methods. In supervised fine-tuning, it not only evicts many tokens but also outperforms LoRA-finetuned LLMs on some datasets, such as RTE, where it improves accuracy by 13.9% while evicting 62.8% of tokens, showing that effective eviction of redundant tokens can even enhance performance.

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed Infini-attention. The Infini-attention incorporates a compressive memory into the vanilla attention mechanism and builds in both masked local attention and long-term linear attention mechanisms in a single Transformer block. We demonstrate the effectiveness of our approach on long-context language modeling benchmarks, 1M sequence length passkey context block retrieval and 500K length book summarization tasks with 1B and 8B LLMs. Our approach introduces minimal bounded memory parameters and enables fast streaming inference for LLMs.

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders, leading to high computational demands, which limits their applicability in resource-constrained environments and for long-context tasks. In this work, we propose a training-free adaptive inference method for multi-modal LLMs that can accommodate a broad range of efficiency requirements with a minimum performance drop. Our method consists of a) iterative token merging based on embedding similarity before LLMs, and b) progressive token pruning within LLM layers based on multi-modal importance. With a minimalist design, our method can be applied to both video and image LLMs. Extensive experiments on diverse video and image benchmarks demonstrate that, our method substantially reduces computation load (e.g., a 7-fold reduction in FLOPs) while preserving the performance of video and image LLMs. Further, under a similar computational cost, our method outperforms the state-of-the-art methods in long video understanding (e.g., +4.6 on MLVU). Additionally, our in-depth analysis provides insights into token redundancy and LLM layer behaviors, offering guidance for future research in designing efficient multi-modal LLMs. Our code will be available at https://github.com/LaVi-Lab/AIM.

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass. However, existing SD approaches require the drafter and target models to share the same vocabulary, thus limiting the pool of possible drafters, often necessitating the training of a drafter from scratch. We present three new SD methods that remove this shared-vocabulary constraint. All three methods preserve the target distribution (i.e., they are lossless) and work with off-the-shelf models without requiring additional training or modifications. Empirically, on summarization, programming, and long-context tasks, our algorithms achieve significant speedups over standard autoregressive decoding. By enabling any off-the-shelf model to serve as drafter and requiring no retraining, this work substantially broadens the applicability of the SD framework in practice.

The size of the key-value (KV) cache plays a critical role in determining both the maximum context length and the number of concurrent requests supported during inference in modern language models. The KV cache size grows proportionally with the number of attention heads and the tokens processed, leading to increased memory consumption and slower inference for long inputs. In this work, we explore the use of MixAttention, a model architecture modification closely related to a blog published by Character.AI. MixAttention combines sliding window attention, where only a small subset of recent tokens is stored in the KV cache, with KV cache sharing across layers. Our experiments demonstrate that MixAttention significantly reduces memory usage and improves inference speed without sacrificing model performance in both short and long-context tasks. We also explore various configurations of this architecture, identifying those that maintain quality across evaluation metrics while optimizing resource efficiency.

Advancements in distributed training and efficient attention mechanisms have significantly expanded the context window sizes of large language models (LLMs). However, recent work reveals that the effective context lengths of open-source LLMs often fall short, typically not exceeding half of their training lengths. In this work, we attribute this limitation to the left-skewed frequency distribution of relative positions formed in LLMs pretraining and post-training stages, which impedes their ability to effectively gather distant information. To address this challenge, we introduce ShifTed Rotray position embeddING (STRING). STRING shifts well-trained positions to overwrite the original ineffective positions during inference, enhancing performance within their existing training lengths. Experimental results show that without additional training, STRING dramatically improves the performance of the latest large-scale models, such as Llama3.1 70B and Qwen2 72B, by over 10 points on popular long-context benchmarks RULER and InfiniteBench, establishing new state-of-the-art results for open-source LLMs. Compared to commercial models, Llama 3.1 70B with \method even achieves better performance than GPT-4-128K and clearly surpasses Claude 2 and Kimi-chat.

In-context Ranking (ICR) is an emerging paradigm for Information Retrieval (IR), which leverages contextual understanding of LLMs by directly incorporating the task description, candidate documents, and the query into the model's input prompt and tasking the LLM to identify relevant document(s). While it is effective, efficiency is a significant challenge in this paradigm, especially as the candidate list grows due to quadratic/super-linear scaling of attention operation with context length. To this end, this paper first identifies inherent and exploitable structures in the attention of LLMs finetuned for ICR: (1) inter-document block sparsity: attention is dense within each document block but sparse across different documents in the context; and (2) query-document block relevance: the attention scores from certain query tokens to a document block in middle layers strongly correlate with that document's actual relevance. Motivated by these observations, we introduce BlockRank (Blockwise In-context Ranking), a novel method that adapts the attention operation in an LLM by (a) architecturally enforcing the observed inter-document block sparsity, reducing attention complexity from quadratic to linear without loss in performance, and (b) optimizing query-document block relevance for true relevant documents during fine-tuning using an auxiliary contrastive training objective, improving retrieval in attention. Experiments on BEIR, MSMarco and NQ with Mistral-7B demonstrate that FLARE Mistral matches or outperforms existing SOTA listwise rankers and controlled fine-tuned baseline while being significantly more efficient at inference (4.7x for 100 MSMarco documents in context) and scaling gracefully to long-context shortlists, around 500 documents in-context (approximately 100K context length) within a second, presenting a scalable and effective solution for ICR.

The long-context capability of recent large transformer models can be surmised to rely on techniques such as attention/model parallelism, as well as hardware-level optimizations. While these strategies allow input lengths to scale to millions of tokens, they do not fundamentally mitigate the quadratic computational and memory complexity of the core attention mechanism. In this paper, we address the challenge of long-context processing on a single device using generic implementations by reducing the quadratic memory footprint and inference cost. Existing approaches to extend the context length for generic single device implementations -- such as token merging and modified attentions -- are often modality specific and attain a suboptimal tradeoff between accuracy and efficiency. To overcome these limitations, we propose MAELRE (Modality Agnostic Efficient Long Range Encoder), a unified and efficient transformer architecture designed for long-range encoding across diverse modalities. MAELRE integrates token merging with attention approximation, progressively merging tokens at different stages of internal computational blocks. It employs a lightweight attention approximation when the number of tokens is large, and switches to standard dot-product attention as the sequence becomes shorter through successive aggregation. We demonstrate that MAELRE achieves superior accuracy while reducing computational cost compared to existing long-context models on classification tasks spanning multiple modalities, including text, time series, audio, and vision.

We present a comprehensive framework for enhancing Retrieval-Augmented Generation (RAG) systems through dynamic retrieval strategies and reinforcement fine-tuning. This approach significantly improves large language models on knowledge-intensive tasks, including opendomain question answering and complex reasoning. Our framework integrates two complementary techniques: Policy-Optimized RetrievalAugmented Generation (PORAG), which optimizes the use of retrieved information, and Adaptive Token-Layer Attention Scoring (ATLAS), which dynamically determines retrieval timing and content based on contextual needs. Together, these techniques enhance both the utilization and relevance of retrieved content, improving factual accuracy and response quality. Designed as a lightweight solution compatible with any Transformer-based LLM without requiring additional training, our framework excels in knowledge-intensive tasks, boosting output accuracy in RAG settings. We further propose CRITIC, a novel method to selectively compress key-value caches by token importance, mitigating memory bottlenecks in long-context applications. The framework also incorporates test-time scaling techniques to dynamically balance reasoning depth and computational resources, alongside optimized decoding strategies for faster inference. Experiments on benchmark datasets show that our framework reduces hallucinations, strengthens domain-specific reasoning, and achieves significant efficiency and scalability gains over traditional RAG systems. This integrated approach advances the development of robust, efficient, and scalable RAG systems across diverse applications.

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a series of methods based on block selection and compression to alleviate this problem, but they either have issues with semantic incompleteness or poor training-inference efficiency. To comprehensively address these challenges, we propose ChunkLLM, a lightweight and pluggable training framework. Specifically, we introduce two components: QK Adapter (Q-Adapter and K-Adapter) and Chunk Adapter. The former is attached to each Transformer layer, serving dual purposes of feature compression and chunk attention acquisition. The latter operates at the bottommost layer of the model, functioning to detect chunk boundaries by leveraging contextual semantic information. During the training phase, the parameters of the backbone remain frozen, with only the QK Adapter and Chunk Adapter undergoing training. Notably, we design an attention distillation method for training the QK Adapter, which enhances the recall rate of key chunks. During the inference phase, chunk selection is triggered exclusively when the current token is detected as a chunk boundary, thereby accelerating model inference. Experimental evaluations are conducted on a diverse set of long-text and short-text benchmark datasets spanning multiple tasks. ChunkLLM not only attains comparable performance on short-text benchmarks but also maintains 98.64% of the performance on long-context benchmarks while preserving a 48.58% key-value cache retention rate. Particularly, ChunkLLM attains a maximum speedup of 4.48x in comparison to the vanilla Transformer in the processing of 120K long texts.

Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specific feature patterns and task performance, which can lead to degraded generalization. In this paper, we propose EvolKV, an adaptive framework for layer-wise, task-driven KV cache compression that jointly optimizes the memory efficiency and task performance. By reformulating cache allocation as a multi-objective optimization problem, EvolKV leverages evolutionary search to dynamically configure layer budgets while directly maximizing downstream performance. Extensive experiments on 11 tasks demonstrate that our approach outperforms all baseline methods across a wide range of KV cache budgets on long-context tasks and surpasses heuristic baselines by up to 7 percentage points on GSM8K. Notably, EvolKV achieves superior performance over the full KV cache setting on code completion while utilizing only 1.5% of the original budget, suggesting the untapped potential in learned compression strategies for KV cache budget allocation.

The growing demand for efficient Large Language Model (LLM) inference requires a holistic optimization on algorithms, systems, and hardware. However, very few works have fundamentally changed the generation pattern: each token needs one forward pass and one KV cache. This can be sub-optimal because we found that LLMs are extremely capable of self-identifying the exact dose of information that a single KV cache can store, and many tokens can be generated confidently without global context. Based on this insight, we introduce HAMburger, a Hierarchically Auto-regressive Model that redefines resource allocation in LLMs by moving beyond uniform computation and storage per token during inference. Stacking a compositional embedder and a micro-step decoder in between a base LLM, HAMburger smashes multiple tokens into a single KV and generates several tokens per step. Additionally, HAMburger functions as a speculative decoding framework where it can blindly trust self-drafted tokens. As a result, HAMburger shifts the growth of KV cache and forward FLOPs from linear to sub-linear with respect to output length, and adjusts its inference speed based on query perplexity and output structure. Extensive evaluations show that HAMburger reduces the KV cache computation by up to 2times and achieves up to 2times TPS, while maintaining quality in both short- and long-context tasks. Our method explores an extremely challenging inference regime that requires both computation- and memory-efficiency with a hardware-agnostic design.

Transformer models rely on self-attention to capture token dependencies but face challenges in effectively integrating positional information while allowing multi-head attention (MHA) flexibility. Prior methods often model semantic and positional differences disparately or apply uniform positional adjustments across heads, potentially limiting representational capacity. This paper introduces ComplexFormer, featuring Complex Multi-Head Attention-CMHA. CMHA empowers each head to independently model semantic and positional differences unified within the complex plane, representing interactions as rotations and scaling. ComplexFormer incorporates two key improvements: (1) a per-head Euler transformation, converting real-valued query/key projections into polar-form complex vectors for head-specific complex subspace operation; and (2) a per-head adaptive differential rotation mechanism, exp[i(Adapt(ASmn,i) + Delta(Pmn),i)], allowing each head to learn distinct strategies for integrating semantic angle differences (ASmn,i) with relative positional encodings (Delta(Pmn),i). Extensive experiments on language modeling, text generation, code generation, and mathematical reasoning show ComplexFormer achieves superior performance, significantly lower generation perplexity , and improved long-context coherence compared to strong baselines like RoPE-Transformers. ComplexFormer demonstrates strong parameter efficiency, offering a more expressive, adaptable attention mechanism.

The utilization of long contexts poses a big challenge for large language models due to their limited context window length. Although the context window can be extended through fine-tuning, it will result in a considerable cost at both training and inference time, and exert an unfavorable impact to the LLM's original capabilities. In this work, we propose Activation Beacon, which condenses LLM's raw activations into more compact forms such that it can perceive a much longer context with a limited context window. Activation Beacon is introduced as a plug-and-play module for the LLM. It fully preserves the LLM's original capability on short contexts while extending the new capability on processing longer contexts. Besides, it works with short sliding windows to process the long context, which achieves a competitive memory and time efficiency in both training and inference. Activation Beacon is learned by the auto-regression task conditioned on a mixture of beacons with diversified condensing ratios. Thanks to such a treatment, it can be efficiently trained purely with short-sequence data in just 10K steps, which consumes less than 9 hours on a single 8xA800 GPU machine. The experimental studies show that Activation Beacon is able to extend Llama-2-7B's context length by times100 times (from 4K to 400K), meanwhile achieving a superior result on both long-context generation and understanding tasks. Our model and code will be available at the BGE repository.

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream 7B, LLaDA 8B) suffer from slow inference. While they match the quality of similarly sized Autoregressive (AR) Models (e.g., Qwen2.5 7B, Llama3 8B), their iterative denoising requires multiple full-sequence forward passes, resulting in high computational costs and latency, particularly for long input prompts and long-context scenarios. Furthermore, parallel token generation introduces token incoherence problems, and current sampling heuristics suffer from significant quality drops with decreasing denoising steps. We address these limitations with two training-free techniques. First, we propose FreeCache, a Key-Value (KV) approximation caching technique that reuses stable KV projections across denoising steps, effectively reducing the computational cost of DLM inference. Second, we introduce Guided Diffusion, a training-free method that uses a lightweight pretrained autoregressive model to supervise token unmasking, dramatically reducing the total number of denoising iterations without sacrificing quality. We conduct extensive evaluations on open-source reasoning benchmarks, and our combined methods deliver up to a 34x end-to-end speedup without compromising accuracy. For the first time, diffusion language models achieve a comparable and even faster latency as the widely adopted autoregressive models. Our work successfully paved the way for scaling up the diffusion language model to a broader scope of applications across different domains.

With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation. To compress the KV cache, recent methods identify critical KV tokens through heuristic ranking with attention scores. However, these methods often struggle to accurately determine critical tokens as they neglect the temporal patterns in attention scores, resulting in a noticeable degradation in LLM performance. To address this challenge, we propose AttentionPredictor, which is the first learning-based critical token identification approach. Specifically, AttentionPredictor learns a lightweight convolution model to capture spatiotemporal patterns and predict the next-token attention score. An appealing feature of AttentionPredictor is that it accurately predicts the attention score while consuming negligible memory. Moreover, we propose a cross-token critical cache prefetching framework that hides the token estimation time overhead to accelerate the decoding stage. By retaining most of the attention information, AttentionPredictor achieves 16times KV cache compression with comparable LLM performance, significantly outperforming the state-of-the-art.

KV caching significantly improves the efficiency of Large Language Model (LLM) inference by storing attention states from previously processed tokens, enabling faster generation of subsequent tokens. However, as sequence length increases, the KV cache quickly becomes a major memory bottleneck. To address this, we propose PagedEviction, a novel fine-grained, structured KV cache pruning strategy that enhances the memory efficiency of vLLM's PagedAttention. Unlike existing approaches that rely on attention-based token importance or evict tokens across different vLLM pages, PagedEviction introduces an efficient block-wise eviction algorithm tailored for paged memory layouts. Our method integrates seamlessly with PagedAttention without requiring any modifications to its CUDA attention kernels. We evaluate PagedEviction across Llama-3.1-8B-Instruct, Llama-3.2-1B-Instruct, and Llama-3.2-3B-Instruct models on the LongBench benchmark suite, demonstrating improved memory usage with better accuracy than baselines on long context tasks.

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively parallel computation capabilities, such as GPUs or TPUs, and aim at long context lengths (e.g., 64K), making them unsuitable for edge scenarios. We present DeltaLLM, a training-free framework that exploits temporal sparsity in attention patterns to enable efficient LLM inference across both the prefilling and decoding stages, on resource-constrained edge devices. DeltaLLM introduces an accuracy- and memory-aware delta matrix construction strategy that introduces temporal sparsity, and a context-aware hybrid attention mechanism that combines full attention in a local context window with delta approximation outside it to increase accuracy. We evaluate our framework on the edge-device-friendly BitNet-b1.58-2B-4T model and Llama3.2-1B-Instruct model across diverse language tasks. The results show that on BitNet, our framework increases the attention sparsity from 0% to 60% during the prefilling stage with slight accuracy improvement on the WG task, and 0% to 57% across both the prefilling and decoding stages, with even higher F1 score from 29.63 to 30.97 on SQuAD-v2 task. On the Llama model, it can also achieve up to 60% sparsity during the prefilling stage and around 57% across both stages with negligible accuracy drop. These results demonstrate that DeltaLLM offers a promising solution for efficient edge deployment, requiring no fine-tuning and seamlessly integrating with existing inference pipelines.

Processing long-context inputs with large language models presents a significant challenge due to the enormous memory requirements of the Key-Value (KV) cache during inference. Existing KV cache compression methods exhibit noticeable performance degradation when memory is reduced by more than 85%. Additionally, strategies that leverage GPU-CPU collaboration for approximate attention remain underexplored in this setting. We propose HCAttention, a heterogeneous attention computation framework that integrates key quantization, value offloading, and dynamic KV eviction to enable efficient inference under extreme memory constraints. The method is compatible with existing transformer architectures and does not require model fine-tuning. Experimental results on the LongBench benchmark demonstrate that our approach preserves the accuracy of full-attention model while shrinking the KV cache memory footprint to 25% of its original size. Remarkably, it stays competitive with only 12.5% of the cache, setting a new state-of-the-art in LLM KV cache compression. To the best of our knowledge, HCAttention is the first to extend the Llama-3-8B model to process 4 million tokens on a single A100 GPU with 80GB memory.

We introduce Qwen2.5-1M, a series of models that extend the context length to 1 million tokens. Compared to the previous 128K version, the Qwen2.5-1M series have significantly enhanced long-context capabilities through long-context pre-training and post-training. Key techniques such as long data synthesis, progressive pre-training, and multi-stage supervised fine-tuning are employed to effectively enhance long-context performance while reducing training costs. To promote the use of long-context models among a broader user base, we present and open-source our inference framework. This framework includes a length extrapolation method that can expand the model context lengths by at least four times, or even more, without additional training. To reduce inference costs, we implement a sparse attention method along with chunked prefill optimization for deployment scenarios and a sparsity refinement method to improve precision. Additionally, we detail our optimizations in the inference engine, including kernel optimization, pipeline parallelism, and scheduling optimization, which significantly enhance overall inference performance. By leveraging our inference framework, the Qwen2.5-1M models achieve a remarkable 3x to 7x prefill speedup in scenarios with 1 million tokens of context. This framework provides an efficient and powerful solution for developing applications that require long-context processing using open-source models. The Qwen2.5-1M series currently includes the open-source models Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, as well as the API-accessed model Qwen2.5-Turbo. Evaluations show that Qwen2.5-1M models have been greatly improved in long-context tasks without compromising performance in short-context scenarios. Specifically, the Qwen2.5-14B-Instruct-1M model significantly outperforms GPT-4o-mini in long-context tasks and supports contexts eight times longer.

Large Language Models (LLMs) have been widely deployed in a variety of applications, and the context length is rapidly increasing to handle tasks such as long-document QA and complex logical reasoning. However, long context poses significant challenges for inference efficiency, including high memory costs of key-value (KV) cache and increased latency due to extensive memory accesses. Recent works have proposed compressing KV cache to approximate computation, but these methods either evict tokens permanently, never recalling them for later inference, or recall previous tokens at the granularity of pages divided by textual positions. Both approaches degrade the model accuracy and output quality. To achieve efficient and accurate recallable KV cache compression, we introduce ClusterKV, which recalls tokens at the granularity of semantic clusters. We design and implement efficient algorithms and systems for clustering, selection, indexing and caching. Experiment results show that ClusterKV attains negligible accuracy loss across various tasks with 32k context lengths, using only a 1k to 2k KV cache budget, and achieves up to a 2times speedup in latency and a 2.5times improvement in decoding throughput. Compared to SoTA recallable KV compression methods, ClusterKV demonstrates higher model accuracy and output quality, while maintaining or exceeding inference efficiency.

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition models usually process a limited number of tokens each time, making attention score calculation less of a bottleneck. Instead, the bottleneck lies in the linear projection layers of multi-head attention and feedforward networks, constituting a substantial portion of the model size and contributing significantly to computation, memory, and power usage. To address this bottleneck, we propose folding attention, a technique targeting these linear layers, significantly reducing model size and improving memory and power efficiency. Experiments on on-device Transformer-based streaming speech recognition models show that folding attention reduces model size (and corresponding memory consumption) by up to 24% and power consumption by up to 23%, all without compromising model accuracy or computation overhead.

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications by leveraging increased model sizes and sequence lengths. However, the associated rise in computational and memory costs poses significant challenges, particularly in managing long sequences due to the quadratic complexity of the transformer attention mechanism. This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference. Unlike existing approaches that optimize the memory based on the sequence lengths, we uncover that the channel dimension of the KV cache exhibits significant redundancy, characterized by unbalanced magnitude distribution and low-rank structure in attention weights. Based on these observations, we propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels. Our approach not only maintains or enhances model accuracy but also achieves a reduction in memory costs by over 20% compared with vanilla KV cache eviction methods. Extensive evaluations on the LLaMA3 and Mistral models across various long-sequence datasets confirm the efficacy of ThinK, setting a new precedent for efficient LLM deployment without compromising performance. We also outline the potential of extending our method to value cache pruning, demonstrating ThinK's versatility and broad applicability in reducing both memory and computational overheads.

Language Models (LMs) assign significant attention to the first token, even if it is not semantically important, which is known as attention sink. This phenomenon has been widely adopted in applications such as streaming/long context generation, KV cache optimization, inference acceleration, model quantization, and others. Despite its widespread use, a deep understanding of attention sink in LMs is still lacking. In this work, we first demonstrate that attention sinks exist universally in LMs with various inputs, even in small models. Furthermore, attention sink is observed to emerge during the LM pre-training, motivating us to investigate how optimization, data distribution, loss function, and model architecture in LM pre-training influence its emergence. We highlight that attention sink emerges after effective optimization on sufficient training data. The sink position is highly correlated with the loss function and data distribution. Most importantly, we find that attention sink acts more like key biases, storing extra attention scores, which could be non-informative and not contribute to the value computation. We also observe that this phenomenon (at least partially) stems from tokens' inner dependence on attention scores as a result of softmax normalization. After relaxing such dependence by replacing softmax attention with other attention operations, such as sigmoid attention without normalization, attention sinks do not emerge in LMs up to 1B parameters. The code is available at https://github.com/sail-sg/Attention-Sink.

The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this issue by selectively dropping tokens, which irreversibly erases critical information that might be needed for future queries. In this paper, we propose a novel compression technique for KV cache that preserves all token information. Our investigation reveals that: i) Most attention heads primarily focus on the local context; ii) Only a few heads, denoted as retrieval heads, can essentially pay attention to all input tokens. These key observations motivate us to use separate caching strategy for attention heads. Therefore, we propose RazorAttention, a training-free KV cache compression algorithm, which maintains a full cache for these crucial retrieval heads and discards the remote tokens in non-retrieval heads. Furthermore, we introduce a novel mechanism involving a "compensation token" to further recover the information in the dropped tokens. Extensive evaluations across a diverse set of large language models (LLMs) demonstrate that RazorAttention achieves a reduction in KV cache size by over 70% without noticeable impacts on performance. Additionally, RazorAttention is compatible with FlashAttention, rendering it an efficient and plug-and-play solution that enhances LLM inference efficiency without overhead or retraining of the original model.

Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has been considerable interest in increasing the context lengths for these models to enhance their applicability to complex tasks. However, at long context lengths and large batch sizes, the key-value (KV) cache, which stores the attention keys and values, emerges as the new bottleneck in memory usage during inference. To address this, we propose Eigen Attention, which performs the attention operation in a low-rank space, thereby reducing the KV cache memory overhead. Our proposed approach is orthogonal to existing KV cache compression techniques and can be used synergistically with them. Through extensive experiments over OPT, MPT, and Llama model families, we demonstrate that Eigen Attention results in up to 40% reduction in KV cache sizes and up to 60% reduction in attention operation latency with minimal drop in performance.

Vision-Language Models (VLMs) have made significant progress in multimodal tasks. However, their performance often deteriorates in long-context scenarios, particularly long videos. While Rotary Position Embedding (RoPE) has been widely adopted for length generalization in Large Language Models (LLMs), extending vanilla RoPE to capture the intricate spatial-temporal dependencies in videos remains an unsolved challenge. Existing methods typically allocate different frequencies within RoPE to encode 3D positional information. However, these allocation strategies mainly rely on heuristics, lacking in-depth theoretical analysis. In this paper, we first study how different allocation strategies impact the long-context capabilities of VLMs. Our analysis reveals that current multimodal RoPEs fail to reliably capture semantic similarities over extended contexts. To address this issue, we propose HoPE, a Hybrid of Position Embedding designed to improve the long-context capabilities of VLMs. HoPE introduces a hybrid frequency allocation strategy for reliable semantic modeling over arbitrarily long context, and a dynamic temporal scaling mechanism to facilitate robust learning and flexible inference across diverse context lengths. Extensive experiments across four video benchmarks on long video understanding and retrieval tasks demonstrate that HoPE consistently outperforms existing methods, confirming its effectiveness. Code is available at https://github.com/hrlics/HoPE.

Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache. Retrieval-based KV cache reduction methods can mitigate these challenges, typically by offloading the complete KV cache to CPU and retrieving necessary tokens on demand during inference. However, these methods still suffer from unsatisfactory accuracy degradation and extra retrieval overhead. To address these limitations, this paper proposes A^2ATS, a novel retrieval-based KV cache reduction method. A^2ATS aims to obtain an accurate approximation of attention scores by applying the vector quantization technique to key states, thereby enabling efficient and precise retrieval of the top-K tokens. First, we propose Windowed Rotary Position Embedding, which decouples the positional dependency from query and key states after position embedding. Then, we propose query-aware vector quantization that optimizes the objective of attention score approximation directly. Finally, we design the heterogeneous inference architecture for KV cache offloading, enabling long context serving with larger batch sizes. Experimental results demonstrate that A^2ATS can achieve a lower performance degradation with similar or lower overhead compared to existing methods, thereby increasing long context serving throughput by up to 2.7 times.

Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. However, as context length grows, the computational cost of attention increases quadratically with the number of tokens, presenting significant efficiency challenges. This paper presents an analysis of various Key-Value (KV) cache compression strategies, offering a comprehensive taxonomy that categorizes these methods by their underlying principles and implementation techniques. Furthermore, we evaluate their impact on performance and inference latency, providing critical insights into their effectiveness. Our findings highlight the trade-offs involved in KV cache compression and its influence on handling long-context scenarios, paving the way for more efficient LLM implementations.

On-device large language models (LLMs) are catalyzing novel mobile applications such as UI task automation and personalized email auto-reply, without giving away users' private data. However, on-device LLMs still suffer from unacceptably long inference latency, especially the time to first token (prefill stage) due to the need of long context for accurate, personalized content generation, as well as the lack of parallel computing capacity of mobile CPU/GPU. To enable practical on-device LLM, we present mllm-NPU, the first-of-its-kind LLM inference system that efficiently leverages on-device Neural Processing Unit (NPU) offloading. Essentially, mllm-NPU is an algorithm-system co-design that tackles a few semantic gaps between the LLM architecture and contemporary NPU design. Specifically, it re-constructs the prompt and model in three levels: (1) At prompt level, it divides variable-length prompts into multiple fixed-sized chunks while maintaining data dependencies; (2) At tensor level, it identifies and extracts significant outliers to run on the CPU/GPU in parallel with minimal overhead; (3) At block level, it schedules Transformer blocks in an out-of-order manner to the CPU/GPU and NPU based on their hardware affinity and sensitivity to accuracy. Compared to competitive baselines, mllm-NPU achieves 22.4x faster prefill speed and 30.7x energy savings on average, and up to 32.8x speedup in an end-to-end real-world application. For the first time, mllm-NPU achieves more than 1,000 tokens/sec prefilling for a billion-sized model (Qwen1.5-1.8B), paving the way towards practical on-device LLM.

Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a compelling balance between modeling quality and computational efficiency, particularly for long-context tasks. While these hybrid models show promising performance, systematic comparisons of hybridization strategies and analyses on the key factors behind their effectiveness have not been clearly shared to the community. In this work, we present a holistic evaluation of hybrid architectures based on inter-layer (sequential) or intra-layer (parallel) fusion. We evaluate these designs from a variety of perspectives: language modeling performance, long-context capabilities, scaling analysis, and training and inference efficiency. By investigating the core characteristics of their computational primitive, we identify the most critical elements for each hybridization strategy and further propose optimal design recipes for both hybrid models. Our comprehensive analysis provides practical guidance and valuable insights for developing hybrid language models, facilitating the optimization of architectural configurations.

We introduce Sigma, an efficient large language model specialized for the system domain, empowered by a novel architecture including DiffQKV attention, and pre-trained on our meticulously collected system domain data. DiffQKV attention significantly enhances the inference efficiency of Sigma by optimizing the Query (Q), Key (K), and Value (V) components in the attention mechanism differentially, based on their varying impacts on the model performance and efficiency indicators. Specifically, we (1) conduct extensive experiments that demonstrate the model's varying sensitivity to the compression of K and V components, leading to the development of differentially compressed KV, and (2) propose augmented Q to expand the Q head dimension, which enhances the model's representation capacity with minimal impacts on the inference speed. Rigorous theoretical and empirical analyses reveal that DiffQKV attention significantly enhances efficiency, achieving up to a 33.36% improvement in inference speed over the conventional grouped-query attention (GQA) in long-context scenarios. We pre-train Sigma on 6T tokens from various sources, including 19.5B system domain data that we carefully collect and 1T tokens of synthesized and rewritten data. In general domains, Sigma achieves comparable performance to other state-of-arts models. In the system domain, we introduce the first comprehensive benchmark AIMicius, where Sigma demonstrates remarkable performance across all tasks, significantly outperforming GPT-4 with an absolute improvement up to 52.5%.

We introduce the Bittensor Language Model, called "BTLM-3B-8K", a new state-of-the-art 3 billion parameter open-source language model. BTLM-3B-8K was trained on 627B tokens from the SlimPajama dataset with a mixture of 2,048 and 8,192 context lengths. BTLM-3B-8K outperforms all existing 3B parameter models by 2-5.5% across downstream tasks. BTLM-3B-8K is even competitive with some 7B parameter models. Additionally, BTLM-3B-8K provides excellent long context performance, outperforming MPT-7B-8K and XGen-7B-8K on tasks up to 8,192 context length. We trained the model on a cleaned and deduplicated SlimPajama dataset; aggressively tuned the \textmu P hyperparameters and schedule; used ALiBi position embeddings; and adopted the SwiGLU nonlinearity. On Hugging Face, the most popular models have 7B parameters, indicating that users prefer the quality-size ratio of 7B models. Compacting the 7B parameter model to one with 3B parameters, with little performance impact, is an important milestone. BTLM-3B-8K needs only 3GB of memory with 4-bit precision and takes 2.5x less inference compute than 7B models, helping to open up access to a powerful language model on mobile and edge devices. BTLM-3B-8K is available under an Apache 2.0 license on Hugging Face: https://huggingface.co/cerebras/btlm-3b-8k-base.

Large language models (LLMs) are great at processing multiple natural language processing tasks, but their abilities are constrained by inferior performance with long context, slow inference speed, and the high cost of computing the results. Deploying LLMs with precise and informative context helps users process large-scale datasets more effectively and cost-efficiently. Existing works rely on compressing long prompt contexts into soft prompts. However, soft prompt compression encounters limitations in transferability across different LLMs, especially API-based LLMs. To this end, this work aims to compress lengthy prompts in the form of natural language with LLM transferability. This poses two challenges: (i) Natural Language (NL) prompts are incompatible with back-propagation, and (ii) NL prompts lack flexibility in imposing length constraints. In this work, we propose a Natural Language Prompt Encapsulation (Nano-Capsulator) framework compressing original prompts into NL formatted Capsule Prompt while maintaining the prompt utility and transferability. Specifically, to tackle the first challenge, the Nano-Capsulator is optimized by a reward function that interacts with the proposed semantics preserving loss. To address the second question, the Nano-Capsulator is optimized by a reward function featuring length constraints. Experimental results demonstrate that the Capsule Prompt can reduce 81.4% of the original length, decrease inference latency up to 4.5x, and save 80.1% of budget overheads while providing transferability across diverse LLMs and different datasets.

Softmax attention is the principle backbone of foundation models for various artificial intelligence applications, yet its quadratic complexity in sequence length can limit its inference throughput in long-context settings. To address this challenge, alternative architectures such as linear attention, State Space Models (SSMs), and Recurrent Neural Networks (RNNs) have been considered as more efficient alternatives. While connections between these approaches exist, such models are commonly developed in isolation and there is a lack of theoretical understanding of the shared principles underpinning these architectures and their subtle differences, greatly influencing performance and scalability. In this paper, we introduce the Dynamical Systems Framework (DSF), which allows a principled investigation of all these architectures in a common representation. Our framework facilitates rigorous comparisons, providing new insights on the distinctive characteristics of each model class. For instance, we compare linear attention and selective SSMs, detailing their differences and conditions under which both are equivalent. We also provide principled comparisons between softmax attention and other model classes, discussing the theoretical conditions under which softmax attention can be approximated. Additionally, we substantiate these new insights with empirical validations and mathematical arguments. This shows the DSF's potential to guide the systematic development of future more efficient and scalable foundation models.

Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI), yet their lack of well-defined memory management systems hinders the development of long-context reasoning, continual personalization, and knowledge consistency.Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.While Retrieval-Augmented Generation (RAG) introduces external knowledge in plain text, it remains a stateless workaround without lifecycle control or integration with persistent representations.Recent work has modeled the training and inference cost of LLMs from a memory hierarchy perspective, showing that introducing an explicit memory layer between parameter memory and external retrieval can substantially reduce these costs by externalizing specific knowledge. Beyond computational efficiency, LLMs face broader challenges arising from how information is distributed over time and context, requiring systems capable of managing heterogeneous knowledge spanning different temporal scales and sources. To address this challenge, we propose MemOS, a memory operating system that treats memory as a manageable system resource. It unifies the representation, scheduling, and evolution of plaintext, activation-based, and parameter-level memories, enabling cost-efficient storage and retrieval. As the basic unit, a MemCube encapsulates both memory content and metadata such as provenance and versioning. MemCubes can be composed, migrated, and fused over time, enabling flexible transitions between memory types and bridging retrieval with parameter-based learning. MemOS establishes a memory-centric system framework that brings controllability, plasticity, and evolvability to LLMs, laying the foundation for continual learning and personalized modeling.

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high computational requirements and limited input sequence length. Despite these separate efforts, no investigation has been done into the intersection of these two fields. In this work, we provide an evaluation of model compression via knowledge distillation on efficient attention transformers. We provide cost-performance trade-offs for the compression of state-of-the-art efficient attention architectures and the gains made in performance in comparison to their full attention counterparts. Furthermore, we introduce a new long-context Named Entity Recognition dataset, GONERD, to train and test the performance of NER models on long sequences. We find that distilled efficient attention transformers can preserve a significant amount of original model performance, preserving up to 98.6% across short-context tasks (GLUE, SQUAD, CoNLL-2003), up to 94.6% across long-context Question-and-Answering tasks (HotpotQA, TriviaQA), and up to 98.8% on long-context Named Entity Recognition (GONERD), while decreasing inference times by up to 57.8%. We find that, for most models on most tasks, performing knowledge distillation is an effective method to yield high-performing efficient attention models with low costs.

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces have dramatically expanded capabilities for real-time data retrieval, complex computation, and multi-step orchestration. Yet, the explosive proliferation of plugins, connectors, and inter-agent protocols has outpaced discovery mechanisms and security practices, resulting in brittle integrations vulnerable to diverse threats. In this survey, we introduce the first unified, end-to-end threat model for LLM-agent ecosystems, spanning host-to-tool and agent-to-agent communications, formalize adversary capabilities and attacker objectives, and catalog over thirty attack techniques. Specifically, we organized the threat model into four domains: Input Manipulation (e.g., prompt injections, long-context hijacks, multimodal adversarial inputs), Model Compromise (e.g., prompt- and parameter-level backdoors, composite and encrypted multi-backdoors, poisoning strategies), System and Privacy Attacks (e.g., speculative side-channels, membership inference, retrieval poisoning, social-engineering simulations), and Protocol Vulnerabilities (e.g., exploits in Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent Network Protocol (ANP), and Agent-to-Agent (A2A) protocol). For each category, we review representative scenarios, assess real-world feasibility, and evaluate existing defenses. Building on our threat taxonomy, we identify key open challenges and future research directions, such as securing MCP deployments through dynamic trust management and cryptographic provenance tracking; designing and hardening Agentic Web Interfaces; and achieving resilience in multi-agent and federated environments. Our work provides a comprehensive reference to guide the design of robust defense mechanisms and establish best practices for resilient LLM-agent workflows.

The self-attention mechanism in the transformer architecture is capable of capturing long-range dependencies and it is the main reason behind its effectiveness in processing sequential data. Nevertheless, despite their success, transformers have two significant drawbacks that still limit their broader applicability: (1) In order to remember past information, the self-attention mechanism requires access to the whole history to be provided as context. (2) The inference cost in transformers is expensive. In this paper we introduce recurrent alternatives to the transformer self-attention mechanism that offer a context-independent inference cost, leverage long-range dependencies effectively, and perform well in practice. We evaluate our approaches in reinforcement learning problems where the aforementioned computational limitations make the application of transformers nearly infeasible. We quantify the impact of the different components of our architecture in a diagnostic environment and assess performance gains in 2D and 3D pixel-based partially-observable environments. When compared to a state-of-the-art architecture, GTrXL, inference in our approach is at least 40% cheaper while reducing memory use in more than 50%. Our approach either performs similarly or better than GTrXL, improving more than 37% upon GTrXL performance on harder tasks.

Natural language inference (NLI) is a fundamental NLP task, investigating the entailment relationship between two texts. Popular NLI datasets present the task at sentence-level. While adequate for testing semantic representations, they fall short for testing contextual reasoning over long texts, which is a natural part of the human inference process. We introduce ConTRoL, a new dataset for ConTextual Reasoning over Long texts. Consisting of 8,325 expert-designed "context-hypothesis" pairs with gold labels, ConTRoL is a passage-level NLI dataset with a focus on complex contextual reasoning types such as logical reasoning. It is derived from competitive selection and recruitment test (verbal reasoning test) for police recruitment, with expert level quality. Compared with previous NLI benchmarks, the materials in ConTRoL are much more challenging, involving a range of reasoning types. Empirical results show that state-of-the-art language models perform by far worse than educated humans. Our dataset can also serve as a testing-set for downstream tasks like Checking Factual Correctness of Summaries.

We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering tradeoffs for inference for large Transformer-based models is important as use cases of these models are growing rapidly throughout application areas. We develop a simple analytical model for inference efficiency to select the best multi-dimensional partitioning techniques optimized for TPU v4 slices based on the application requirements. We combine these with a suite of low-level optimizations to achieve a new Pareto frontier on the latency and model FLOPS utilization (MFU) tradeoffs on 500B+ parameter models that outperforms the FasterTransformer suite of benchmarks. We further show that with appropriate partitioning, the lower memory requirements of multiquery attention (i.e. multiple query heads share single key/value head) enables scaling up to 32x larger context lengths. Finally, we achieve a low-batch-size latency of 29ms per token during generation (using int8 weight quantization) and a 76% MFU during large-batch-size processing of input tokens, while supporting a long 2048-token context length on the PaLM 540B parameter model.

For the purpose of efficient and cost-effective large-scale data labeling, crowdsourcing is increasingly being utilized. To guarantee the quality of data labeling, multiple annotations need to be collected for each data sample, and truth inference algorithms have been developed to accurately infer the true labels. Despite previous studies having released public datasets to evaluate the efficacy of truth inference algorithms, these have typically focused on a single type of crowdsourcing task and neglected the temporal information associated with workers' annotation activities. These limitations significantly restrict the practical applicability of these algorithms, particularly in the context of long-term and online truth inference. In this paper, we introduce a substantial crowdsourcing annotation dataset collected from a real-world crowdsourcing platform. This dataset comprises approximately two thousand workers, one million tasks, and six million annotations. The data was gathered over a period of approximately six months from various types of tasks, and the timestamps of each annotation were preserved. We analyze the characteristics of the dataset from multiple perspectives and evaluate the effectiveness of several representative truth inference algorithms on this dataset. We anticipate that this dataset will stimulate future research on tracking workers' abilities over time in relation to different types of tasks, as well as enhancing online truth inference.

Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Video-LLM often face trade-offs among fine-grained visual understanding, long-term context modeling and computational efficiency. We introduce StreamVLN, a streaming VLN framework that employs a hybrid slow-fast context modeling strategy to support multi-modal reasoning over interleaved vision, language and action inputs. The fast-streaming dialogue context facilitates responsive action generation through a sliding-window of active dialogues, while the slow-updating memory context compresses historical visual states using a 3D-aware token pruning strategy. With this slow-fast design, StreamVLN achieves coherent multi-turn dialogue through efficient KV cache reuse, supporting long video streams with bounded context size and inference cost. Experiments on VLN-CE benchmarks demonstrate state-of-the-art performance with stable low latency, ensuring robustness and efficiency in real-world deployment. The project page is: https://streamvln.github.io/{https://streamvln.github.io/}.

In this paper, we introduce RWKV-X, a novel hybrid architecture that combines the efficiency of RWKV for short-range modeling with a sparse attention mechanism designed to capture long-range context. Unlike previous hybrid approaches that rely on full attention layers and retain quadratic complexity, RWKV-X achieves linear-time complexity in training and constant-time complexity in inference decoding. We demonstrate that RWKV-X, when continually pretrained on 64K-token sequences, achieves near-perfect accuracy on the 64K passkey retrieval benchmark. It consistently outperforms prior RWKV-7 models on long-context benchmarks, while maintaining strong performance on short-context tasks. These results highlight RWKV-X as a scalable and efficient backbone for general-purpose language modeling, capable of decoding sequences up to 1 million tokens with stable speed and memory usage. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at: https://github.com/howard-hou/RWKV-X.

Improving time-to-first-token (TTFT) is an essentially important objective in modern large language model (LLM) inference engines. Optimizing TTFT directly results in higher maximal QPS and meets the requirements of many critical applications. However, boosting TTFT is notoriously challenging since it is compute-bounded and the performance bottleneck shifts from the self-attention that many prior works focus on to the MLP part. In this work, we present SpecPrefill, a training free framework that accelerates the inference TTFT for both long and medium context queries based on the following insight: LLMs are generalized enough to preserve the quality given only a carefully chosen subset of prompt tokens. At its core, SpecPrefill leverages a lightweight model to speculate locally important tokens based on the context. These tokens, along with the necessary positional information, are then sent to the main model for processing. We evaluate SpecPrefill with a diverse set of tasks, followed by a comprehensive benchmarking of performance improvement both in a real end-to-end setting and ablation studies. SpecPrefill manages to serve Llama-3.1-405B-Instruct-FP8 with up to 7times maximal end-to-end QPS on real downstream tasks and 7.66times TTFT improvement.

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate these challenges have relied on fixed sparse attention patterns or identifying sparse attention patterns based on limited cases. However, these methods lacked the flexibility to efficiently adapt to varying input demands. In this paper, we introduce FlexPrefill, a Flexible sparse Pre-filling mechanism that dynamically adjusts sparse attention patterns and computational budget in real-time to meet the specific requirements of each input and attention head. The flexibility of our method is demonstrated through two key innovations: 1) Query-Aware Sparse Pattern Determination: By measuring Jensen-Shannon divergence, this component adaptively switches between query-specific diverse attention patterns and predefined attention patterns. 2) Cumulative-Attention Based Index Selection: This component dynamically selects query-key indexes to be computed based on different attention patterns, ensuring the sum of attention scores meets a predefined threshold. FlexPrefill adaptively optimizes the sparse pattern and sparse ratio of each attention head based on the prompt, enhancing efficiency in long-sequence inference tasks. Experimental results show significant improvements in both speed and accuracy over prior methods, providing a more flexible and efficient solution for LLM inference.

To break the context limits of large language models (LLMs) that bottleneck reasoning accuracy and efficiency, we propose the Thread Inference Model (TIM), a family of LLMs trained for recursive and decompositional problem solving, and TIMRUN, an inference runtime enabling long-horizon structured reasoning beyond context limits. Together, TIM hosted on TIMRUN supports virtually unlimited working memory and multi-hop tool calls within a single language model inference, overcoming output limits, positional-embedding constraints, and GPU-memory bottlenecks. Performance is achieved by modeling natural language as reasoning trees measured by both length and depth instead of linear sequences. The reasoning trees consist of tasks with thoughts, recursive subtasks, and conclusions based on the concept we proposed in Schroeder et al, 2025. During generation, we maintain a working memory that retains only the key-value states of the most relevant context tokens, selected by a rule-based subtask-pruning mechanism, enabling reuse of positional embeddings and GPU memory pages throughout reasoning. Experimental results show that our system sustains high inference throughput, even when manipulating up to 90% of the KV cache in GPU memory. It also delivers accurate reasoning on mathematical tasks and handles information retrieval challenges that require long-horizon reasoning and multi-hop tool use.

Long text generation, such as novel writing and discourse-level translation with extremely long contexts, presents significant challenges to current language models. Existing methods mainly focus on extending the model's context window through strategies like length extrapolation. However, these approaches demand substantial hardware resources during the training and/or inference phases. Our proposed method, Temp-Lora, introduces an alternative concept. Instead of relying on the KV cache to store all context information, we embeds this information directly into a temporary Lora module. In the process of long text generation, this module is progressively trained with text generated previously. This approach not only efficiently preserves contextual knowledge but also prevents any permanent alteration to the model's parameters given that the module is discarded post-generation. Extensive experiments on the PG19 language modeling benchmark and the GuoFeng discourse-level translation benchmark validate the effectiveness of Temp-Lora. Our results show that: 1) Temp-Lora substantially enhances generation quality for long text, as indicated by a 13.2% decrease in perplexity (PPL) on a subset of PG19, and a 29.3% decrease in PPL along with a 113.2% increase in BLEU score on a subset of GuoFeng, 2) Temp-Lora is compatible with and enhances most existing long text generation methods, and 3) Temp-Lora can greatly reduce computational costs by shortening the context window. For example, we can ensure a moderate improvement in generation quality (a decrease of 3.8% in PPL) while enabling a 51.5% memory usage reduction and a 60.0% decrease in latency for inference.

AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where multi-agent systems with diverse, task-specialized agents complement one another through structured communication and collaboration. Today, coordination is usually handled with imprecise, ad-hoc natural language, which limits complex interaction and hinders interoperability with domain-specific agents. We introduce Agent context protocols (ACPs): a domain- and agent-agnostic family of structured protocols for agent-agent communication, coordination, and error handling. ACPs combine (i) persistent execution blueprints -- explicit dependency graphs that store intermediate agent outputs -- with (ii) standardized message schemas, enabling robust and fault-tolerant multi-agent collective inference. ACP-powered generalist systems reach state-of-the-art performance: 28.3 % accuracy on AssistantBench for long-horizon web assistance and best-in-class multimodal technical reports, outperforming commercial AI systems in human evaluation. ACPs are highly modular and extensible, allowing practitioners to build top-tier generalist agents quickly.

Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation that improves computational efficiency by sharding attention across multiple hosts while minimizing communication overhead. In the first phase, the context is processed using blockwise-local attention across hosts, in parallel. In the second phase, query and response tokens attend to all prior cached tokens through sequence-global attention. Star Attention integrates seamlessly with most Transformer-based LLMs trained with global attention, reducing memory requirements and inference time by up to 11x while preserving 95-100% of accuracy.

The quadratic complexity and weak length extrapolation of Transformers limits their ability to scale to long sequences, and while sub-quadratic solutions like linear attention and state space models exist, they empirically underperform Transformers in pretraining efficiency and downstream task accuracy. We introduce Megalodon, a neural architecture for efficient sequence modeling with unlimited context length. Megalodon inherits the architecture of Mega (exponential moving average with gated attention), and further introduces multiple technical components to improve its capability and stability, including complex exponential moving average (CEMA), timestep normalization layer, normalized attention mechanism and pre-norm with two-hop residual configuration. In a controlled head-to-head comparison with Llama2, Megalodon achieves better efficiency than Transformer in the scale of 7 billion parameters and 2 trillion training tokens. Megalodon reaches a training loss of 1.70, landing mid-way between Llama2-7B (1.75) and 13B (1.67). Code: https://github.com/XuezheMax/megalodon

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding capabilities in modeling long texts. Existing work attempts to address this issue by introducing long video-text pairs during training. However, these approaches require substantial computational and data resources. In this paper, we tackle the challenge of long video understanding from the perspective of context windows, aiming to apply LMMs to long video tasks without retraining on long video datasets. We first conduct an in-depth analysis of why pretrained LMMs struggle to understand lengthy video content, identifying that discrepancies between visual and language modalities lead to different context windows for visual and language tokens, making it difficult to directly extend the visual tokens to match the language context window. Based on this, we propose to adapt LMMs for long video understanding tasks by extending the visual context window, eliminating the need for retraining on large scalelong video datasets. To further mitigate the significant memory consumption caused by long sequences, we introduce a progressive pooling inference strategy that selectively adjusts the spatial resolution of frame embeddings, reducing the number of visual tokens while retaining important spatial information. Across multiple long video understanding benchmarks, our method consistently improves the performance as the number of video frames increases. On the MLVU benchmark, our method outperforms GPT-4o, even though our model size is only 7B. Additionally, in the 256-frame setting, our method reduces memory usage by approximately 45% compared to the baseline, without introducing any performance loss.

Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, where the model learns to do a downstream task simply by conditioning on a prompt consisting of input-output examples. The LM learns from these examples without being explicitly pretrained to learn. Thus, it is unclear what enables in-context learning. In this paper, we study how in-context learning can emerge when pretraining documents have long-range coherence. Here, the LM must infer a latent document-level concept to generate coherent next tokens during pretraining. At test time, in-context learning occurs when the LM also infers a shared latent concept between examples in a prompt. We prove when this occurs despite a distribution mismatch between prompts and pretraining data in a setting where the pretraining distribution is a mixture of HMMs. In contrast to messy large-scale datasets used to train LMs capable of in-context learning, we generate a small-scale synthetic dataset (GINC) where Transformers and LSTMs both exhibit in-context learning. Beyond the theory, experiments on GINC exhibit large-scale real-world phenomena including improved in-context performance with model scaling (despite the same pretraining loss), sensitivity to example order, and instances where zero-shot is better than few-shot in-context learning.

Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between inference and training workloads. This serial context switching violates the single-program-multiple-data (SPMD) assumption underlying today's distributed training systems. We present Echo, the RL system that cleanly decouples these two phases across heterogeneous "inference" and "training" swarms while preserving statistical efficiency. Echo introduces two lightweight synchronization protocols: a sequential pull mode that refreshes policy weights according to API call for minimal bias, and an asynchronous push-pull mode that streams version-tagged rollouts through a replay buffer to maximise hardware utilisation. Training four representative RL workloads with Qwen3-4B, Qwen2.5-7B, Qwen3-30B-A3B-Thinking-2507 and Qwen3-32B on a geographically distributed cluster, Echo matches a fully co-located Verl baseline in convergence speed and final reward while off-loading trajectory generation to commodity edge hardware. These promising results demonstrate that large-scale RL for LLMs could achieve datacentre-grade performance using decentralised, heterogeneous resources.

Low-rank Adaptation (LoRA) has demonstrated remarkable capabilities for task specific fine-tuning. However, in scenarios that involve multiple tasks, training a separate LoRA model for each one results in considerable inefficiency in terms of storage and inference. Moreover, existing parameter generation methods fail to capture the correlations among these tasks, making multi-task LoRA parameter generation challenging. To address these limitations, we propose In-Context Meta LoRA (ICM-LoRA), a novel approach that efficiently achieves task-specific customization of large language models (LLMs). Specifically, we use training data from all tasks to train a tailored generator, Conditional Variational Autoencoder (CVAE). CVAE takes task descriptions as inputs and produces task-aware LoRA weights as outputs. These LoRA weights are then merged with LLMs to create task-specialized models without the need for additional fine-tuning. Furthermore, we utilize in-context meta-learning for knowledge enhancement and task mapping, to capture the relationship between tasks and parameter distributions. As a result, our method achieves more accurate LoRA parameter generation for diverse tasks using CVAE. ICM-LoRA enables more accurate LoRA parameter reconstruction than current parameter reconstruction methods and is useful for implementing task-specific enhancements of LoRA parameters. At the same time, our method occupies 283MB, only 1\% storage compared with the original LoRA.

Large language models are well-known to be effective at few-shot in-context learning (ICL). Recent advancements in multimodal foundation models have enabled unprecedentedly long context windows, presenting an opportunity to explore their capability to perform ICL with many more demonstrating examples. In this work, we evaluate the performance of multimodal foundation models scaling from few-shot to many-shot ICL. We benchmark GPT-4o and Gemini 1.5 Pro across 10 datasets spanning multiple domains (natural imagery, medical imagery, remote sensing, and molecular imagery) and tasks (multi-class, multi-label, and fine-grained classification). We observe that many-shot ICL, including up to almost 2,000 multimodal demonstrating examples, leads to substantial improvements compared to few-shot (<100 examples) ICL across all of the datasets. Further, Gemini 1.5 Pro performance continues to improve log-linearly up to the maximum number of tested examples on many datasets. Given the high inference costs associated with the long prompts required for many-shot ICL, we also explore the impact of batching multiple queries in a single API call. We show that batching up to 50 queries can lead to performance improvements under zero-shot and many-shot ICL, with substantial gains in the zero-shot setting on multiple datasets, while drastically reducing per-query cost and latency. Finally, we measure ICL data efficiency of the models, or the rate at which the models learn from more demonstrating examples. We find that while GPT-4o and Gemini 1.5 Pro achieve similar zero-shot performance across the datasets, Gemini 1.5 Pro exhibits higher ICL data efficiency than GPT-4o on most datasets. Our results suggest that many-shot ICL could enable users to efficiently adapt multimodal foundation models to new applications and domains. Our codebase is publicly available at https://github.com/stanfordmlgroup/ManyICL .

While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited compared to transformer-based models. In this study, we investigate the long-context efficiency issues of the Mamba models and propose ReMamba, which enhances Mamba's ability to comprehend long contexts. ReMamba incorporates selective compression and adaptation techniques within a two-stage re-forward process, incurring minimal additional inference costs overhead. Experimental results on the LongBench and L-Eval benchmarks demonstrate ReMamba's efficacy, improving over the baselines by 3.2 and 1.6 points, respectively, and attaining performance almost on par with same-size transformer models.

The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a fraction is used per prompt, and impractical for edge devices with limited inference-time memory and compute. We address this shortcoming by a memory-augmented architecture and a pretraining strategy aligned with existing hardware paradigms. We introduce small language models that access large hierarchical parametric memory banks encoding world knowledge. During pretraining and inference, we fetch a small, context-dependent memory block and add it to the model. Our pretraining learns to store long-tail world knowledge in the memory parameters, while the small language model acts as an anchor capturing common knowledge and general reasoning abilities. Through trillion-token-scale experiments, we show significant gains: a 160M-parameters model augmented with an 18M-parameters memory fetched from a 4.6B memory bank obtains comparable performance to a regular model with more than 2x the parameters. Through extensive experiments, we study the optimal type and size of parametric memories in transformers, scaling them to over 21B parameters. We find that our proposed hierarchical feed-forward memories work robustly across transformer architectures, whether added during pretraining or post-hoc.

VRAM requirements for transformer models scale quadratically with context length due to the self-attention mechanism. In this paper we modify the decoder-only transformer, replacing self-attention with InAttention, which scales linearly with context length during inference by having tokens attend only to initial states. Benchmarking shows that InAttention significantly reduces VRAM usage during inference, enabling handling of long sequences on consumer GPUs. We corroborate that fine-tuning extends context length efficiently, improving performance on long sequences without high training costs. InAttention offers a scalable solution for long-range dependencies in transformer models, paving the way for further optimization.

The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conversation rounds continue, it is required to store a large amount of KV cache in GPU memory, which significantly affects the efficiency and even availability of the model serving systems. This paper analyzes dialogue data from real users and discovers that the LLM inference manifests a watershed layer, after which the distribution of round-level attention shows notable similarity. We propose Round Attention, a novel round-level attention mechanism that only recalls and computes the KV cache of the most relevant rounds. The experiments show that our method saves 55\% memory usage without compromising model performance.

To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a method called Recurrent Context Compression (RCC), designed to efficiently expand the context window length of LLMs within constrained storage space. We also investigate the issue of poor model responses when both instructions and context are compressed in downstream tasks, and propose an instruction reconstruction method to mitigate this problem. We validated the effectiveness of our approach on multiple tasks, achieving a compression rate of up to 32x on text reconstruction tasks with a BLEU4 score close to 0.95, and nearly 100\% accuracy on a passkey retrieval task with a sequence length of 1M. Finally, our method demonstrated competitive performance in long-text question-answering tasks compared to non-compressed methods, while significantly saving storage resources in long-text inference tasks. Our code, models, and demo are available at https://github.com/WUHU-G/RCC_Transformer

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of large volumes of information. Recognizing the inherent challenges in extending the context window for LLMs, primarily built on Transformer architecture, we propose a new model architecture, referred to as Zebra. This architecture efficiently manages the quadratic time and memory complexity issues associated with full attention in the Transformer by employing grouped local-global attention layers. Our model, akin to a zebra's alternating stripes, balances local and global attention layers, significantly reducing computational requirements and memory consumption. Comprehensive experiments, including pretraining from scratch, continuation of long context adaptation training, and long instruction tuning, are conducted to evaluate the Zebra's performance. The results show that Zebra achieves comparable or superior performance on both short and long sequence benchmarks, while also enhancing training and inference efficiency.

The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe issues on memory footprint and inference latency. In this work, we propose a plug-and-play approach that is able to incrementally compress the intermediate activation of a specified span of tokens into compact ones, thereby reducing both memory and computational cost when processing subsequent context. Experiments on both in-domain language modeling and zero-shot open-ended document generation demonstrate the advantage of our approach over sparse attention baselines in terms of fluency, n-gram matching, and semantic similarity. At last, we comprehensively profile the benefit of context compression on improving the system throughout. Code is available at https://github.com/DRSY/KV_Compression.

While recent advances in reasoning models have demonstrated cognitive behaviors through reinforcement learning, existing approaches struggle to invoke deep reasoning capabilities in multi-turn agents with long-horizon interactions. We propose DeepMiner, a novel framework that elicits such abilities by introducing high-difficulty training tasks and dynamic context window. DeepMiner presents a reverse construction method to generate complex but verifiable question-answer pairs from authentic web sources, which ensures the challenge and reliability of training data while injecting cognitive capabilities into multi-turn reasoning scenarios. We further design an elegant yet effective dynamic context management strategy for both training and inference, utilizing sliding window mechanisms while eliminating the dependency on external summarization models, thereby efficiently empowering the model to handle continuously expanding long-horizon contexts. Through reinforcement learning on Qwen3-32B, we develop DeepMiner-32B, which achieves substantial performance improvements across multiple search agent benchmarks. DeepMiner attains 33.5% accuracy on BrowseComp-en, surpassing the previous best open-source agent by almost 20 percentage points, and demonstrates consistent improvements on BrowseComp-zh, XBench-DeepSearch, and GAIA. Notably, our dynamic context management enables sustained interactions of nearly 100 turns within standard 32k context length, effectively addressing the context limitations that constrain existing multi-turn interaction systems.

This work elicits LLMs' inherent ability to handle long contexts without fine-tuning. The limited length of the training sequence during training may limit the application of Large Language Models (LLMs) on long input sequences for inference. In this work, we argue that existing LLMs themselves have inherent capabilities for handling long contexts. Based on this argument, we suggest extending LLMs' context window by themselves to fully utilize the inherent ability.We propose Self-Extend to stimulate LLMs' long context handling potential. The basic idea is to construct bi-level attention information: the group level and the neighbor level. The two levels are computed by the original model's self-attention, which means the proposed does not require any training. With only four lines of code modification, the proposed method can effortlessly extend existing LLMs' context window without any fine-tuning. We conduct comprehensive experiments and the results show that the proposed method can effectively extend existing LLMs' context window's length.

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to its inherently sequential process. To overcome these challenges, we propose leap multi-token prediction~(L-MTP), an innovative token prediction method that extends the capabilities of multi-token prediction (MTP) by introducing a leap-based mechanism. Unlike conventional MTP, which generates multiple tokens at adjacent positions, L-MTP strategically skips over intermediate tokens, predicting non-sequential ones in a single forward pass. This structured leap not only enhances the model's ability to capture long-range dependencies but also enables a decoding strategy specially optimized for non-sequential leap token generation, effectively accelerating inference. We theoretically demonstrate the benefit of L-MTP in improving inference efficiency. Experiments across diverse benchmarks validate its merit in boosting both LLM performance and inference speed. The source code is available at https://github.com/Xiaohao-Liu/L-MTP.

Real-world applications like video gaming and virtual reality often demand the ability to model 3D scenes that users can explore along custom camera trajectories. While significant progress has been made in generating 3D objects from text or images, creating long-range, 3D-consistent, explorable 3D scenes remains a complex and challenging problem. In this work, we present Voyager, a novel video diffusion framework that generates world-consistent 3D point-cloud sequences from a single image with user-defined camera path. Unlike existing approaches, Voyager achieves end-to-end scene generation and reconstruction with inherent consistency across frames, eliminating the need for 3D reconstruction pipelines (e.g., structure-from-motion or multi-view stereo). Our method integrates three key components: 1) World-Consistent Video Diffusion: A unified architecture that jointly generates aligned RGB and depth video sequences, conditioned on existing world observation to ensure global coherence 2) Long-Range World Exploration: An efficient world cache with point culling and an auto-regressive inference with smooth video sampling for iterative scene extension with context-aware consistency, and 3) Scalable Data Engine: A video reconstruction pipeline that automates camera pose estimation and metric depth prediction for arbitrary videos, enabling large-scale, diverse training data curation without manual 3D annotations. Collectively, these designs result in a clear improvement over existing methods in visual quality and geometric accuracy, with versatile applications.

Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos is still challenging, as their long-context nature results in significant computational and memory overhead. Most existing work treats long videos in the same way as short videos, which is inefficient for real-world applications and hard to generalize to even longer videos. To address these issues, we propose Flash-VStream, an efficient video language model capable of processing extremely long videos and responding to user queries in real time. Particularly, we design a Flash Memory module, containing a low-capacity context memory to aggregate long-context temporal information and model the distribution of information density, and a high-capacity augmentation memory to retrieve detailed spatial information based on this distribution. Compared to existing models, Flash-VStream achieves significant reductions in inference latency. Extensive experiments on long video benchmarks and comprehensive video benchmarks, i.e., EgoSchema, MLVU, LVBench, MVBench and Video-MME, demonstrate the state-of-the-art performance and outstanding efficiency of our method. Code is available at https://github.com/IVGSZ/Flash-VStream.

Multi-modal large language models (MLLMs) have demonstrated considerable potential across various downstream tasks that require cross-domain knowledge. MLLMs capable of processing videos, known as Video-MLLMs, have attracted broad interest in video-language understanding. However, videos, especially long videos, contain more visual tokens than images, making them difficult for LLMs to process. Existing works either downsample visual features or extend the LLM context size, risking the loss of high-resolution information or slowing down inference speed. To address these limitations, we apply cross-attention layers in the intermediate projector between the visual encoder and the large language model (LLM). As the naive cross-attention mechanism is insensitive to temporal order, we further introduce causal cross-attention masks (CCAMs) within the cross-attention layers. This Video-MLLM, named Video-CCAM, is trained in a straightforward two-stage fashion: feature alignment and visual instruction tuning. We develop several Video-CCAM models based on LLMs of different sizes (4B, 9B, and 14B). Video-CCAM proves to be a robust Video-MLLM and shows outstanding performance from short videos to long ones. Among standard video benchmarks like MVBench and VideoChatGPT-QA, Video-CCAM shows outstanding performances (1st/2nd/3rd in MVBench and TGIF-QA, 2nd/3rd/4th in MSVD-QA, MSRVTT-QA, and ActivityNet-QA). In benchmarks encompassing long videos, Video-CCAM models can be directly adapted to long video understanding and still achieve exceptional scores despite being trained solely with images and 16-frame videos. Using 96 frames (6times the training number of frames), Video-CCAM models rank 1st/2nd/3rd in VideoVista and 1st/2nd/4th in MLVU among all open-source Video-MLLMs, respectively. The code is publicly available in https://github.com/QQ-MM/Video-CCAM.

Experts in various fields routinely perform methodical writing tasks to plan, organize, and report their work. From a clinician writing a differential diagnosis for a patient, to a teacher writing a lesson plan for students, these tasks are pervasive, requiring to methodically generate structured long-form output for a given input. We develop a typology of methodical tasks structured in the form of a task objective, procedure, input, and output, and introduce DoLoMiTes, a novel benchmark with specifications for 519 such tasks elicited from hundreds of experts from across 25 fields. Our benchmark further contains specific instantiations of methodical tasks with concrete input and output examples (1,857 in total) which we obtain by collecting expert revisions of up to 10 model-generated examples of each task. We use these examples to evaluate contemporary language models highlighting that automating methodical tasks is a challenging long-form generation problem, as it requires performing complex inferences, while drawing upon the given context as well as domain knowledge.

This paper introduces Neurocache, an approach to extend the effective context size of large language models (LLMs) using an external vector cache to store its past states. Like recent vector retrieval approaches, Neurocache uses an efficient k-nearest-neighbor (kNN) algorithm to retrieve relevant past states and incorporate them into the attention process. Neurocache improves upon previous methods by (1) storing compressed states, which reduces cache size; (2) performing a single retrieval operation per token which increases inference speed; and (3) extending the retrieval window to neighboring states, which improves both language modeling and downstream task accuracy. Our experiments show the effectiveness of Neurocache both for models trained from scratch and for pre-trained models such as Llama2-7B and Mistral-7B when enhanced with the cache mechanism. We also compare Neurocache with text retrieval methods and show improvements in single-document question-answering and few-shot learning tasks. We made the source code available under: https://github.com/alisafaya/neurocache

Reviewing contracts is a time-consuming procedure that incurs large expenses to companies and social inequality to those who cannot afford it. In this work, we propose "document-level natural language inference (NLI) for contracts", a novel, real-world application of NLI that addresses such problems. In this task, a system is given a set of hypotheses (such as "Some obligations of Agreement may survive termination.") and a contract, and it is asked to classify whether each hypothesis is "entailed by", "contradicting to" or "not mentioned by" (neutral to) the contract as well as identifying "evidence" for the decision as spans in the contract. We annotated and release the largest corpus to date consisting of 607 annotated contracts. We then show that existing models fail badly on our task and introduce a strong baseline, which (1) models evidence identification as multi-label classification over spans instead of trying to predict start and end tokens, and (2) employs more sophisticated context segmentation for dealing with long documents. We also show that linguistic characteristics of contracts, such as negations by exceptions, are contributing to the difficulty of this task and that there is much room for improvement.

Language models for biological and chemical sequences enable crucial applications such as drug discovery, protein engineering, and precision medicine. Currently, these language models are predominantly based on Transformer architectures. While Transformers have yielded impressive results, their quadratic runtime dependency on the sequence length complicates their use for long genomic sequences and in-context learning on proteins and chemical sequences. Recently, the recurrent xLSTM architecture has been shown to perform favorably compared to Transformers and modern state-space model (SSM) architectures in the natural language domain. Similar to SSMs, xLSTMs have a linear runtime dependency on the sequence length and allow for constant-memory decoding at inference time, which makes them prime candidates for modeling long-range dependencies in biological and chemical sequences. In this work, we tailor xLSTM towards these domains and propose a suite of architectural variants called Bio-xLSTM. Extensive experiments in three large domains, genomics, proteins, and chemistry, were performed to assess xLSTM's ability to model biological and chemical sequences. The results show that models based on Bio-xLSTM a) can serve as proficient generative models for DNA, protein, and chemical sequences, b) learn rich representations for those modalities, and c) can perform in-context learning for proteins and small molecules.

The Transformer architecture has become a cornerstone of modern artificial intelligence, but its core self-attention mechanism suffers from a complexity bottleneck that scales quadratically with sequence length, severely limiting its application in long-sequence tasks. To address this challenge, existing linear attention methods typically sacrifice model performance by relying on data-agnostic kernel approximations or restrictive context selection. This paper returns to the first principles of connectionism, starting from the topological structure of information flow, to introduce a novel linear attention architecture-TLinFormer. By reconfiguring neuron connection patterns, TLinFormer achieves strict linear complexity while computing exact attention scores and ensuring information flow remains aware of the full historical context. This design aims to bridge the performance gap prevalent between existing efficient attention methods and standard attention. Through a series of experiments, we systematically evaluate the performance of TLinFormer against a standard Transformer baseline on long-sequence inference tasks. The results demonstrate that TLinFormer exhibits overwhelming advantages in key metrics such as inference latency, KV cache efficiency, memory footprint, and overall speedup.

We introduce MiniMax-01 series, including MiniMax-Text-01 and MiniMax-VL-01, which are comparable to top-tier models while offering superior capabilities in processing longer contexts. The core lies in lightning attention and its efficient scaling. To maximize computational capacity, we integrate it with Mixture of Experts (MoE), creating a model with 32 experts and 456 billion total parameters, of which 45.9 billion are activated for each token. We develop an optimized parallel strategy and highly efficient computation-communication overlap techniques for MoE and lightning attention. This approach enables us to conduct efficient training and inference on models with hundreds of billions of parameters across contexts spanning millions of tokens. The context window of MiniMax-Text-01 can reach up to 1 million tokens during training and extrapolate to 4 million tokens during inference at an affordable cost. Our vision-language model, MiniMax-VL-01 is built through continued training with 512 billion vision-language tokens. Experiments on both standard and in-house benchmarks show that our models match the performance of state-of-the-art models like GPT-4o and Claude-3.5-Sonnet while offering 20-32 times longer context window. We publicly release MiniMax-01 at https://github.com/MiniMax-AI.

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves improved segmentation of PASCAL VOC (30% relative improvement to 67.2% mean IU on 2012), NYUDv2, SIFT Flow, and PASCAL-Context, while inference takes one tenth of a second for a typical image.

While inference-time scaling enables LLMs to carry out increasingly long and capable reasoning traces, the patterns and insights uncovered during these traces are immediately discarded once the context window is reset for a new query. External memory is a natural way to persist these discoveries, and recent work has shown clear benefits for reasoning-intensive tasks. We see an opportunity to make such memories more broadly reusable and scalable by moving beyond instance-based memory entries (e.g. exact query/response pairs, or summaries tightly coupled with the original problem context) toward concept-level memory: reusable, modular abstractions distilled from solution traces and stored in natural language. For future queries, relevant concepts are selectively retrieved and integrated into the prompt, enabling test-time continual learning without weight updates. Our design introduces new strategies for abstracting takeaways from rollouts and retrieving entries for new queries, promoting reuse and allowing memory to expand with additional experiences. We evaluate on ARC-AGI, a benchmark that stresses compositional generalization and abstract reasoning, making it a natural fit for concept memory. Our method yields a 7.5% relative gain over a strong no-memory baseline with performance continuing to scale with inference compute. We find abstract concepts to be the most consistent memory design, outscoring the baseline at all tested inference compute scales. Moreover, dynamically updating memory during test-time outperforms fixed settings, supporting the hypothesis that accumulating and abstracting patterns enables further solutions in a form of self-improvement. Code is available at https://github.com/matt-seb-ho/arc_memo.