Papers
arxiv:2512.00722

SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs

Published on Nov 30
· Submitted by Jiaming Xu (SII) on Dec 2
Authors:
,
,
,
,
,
,

Abstract

SpeContext leverages a distilled language model for efficient long-context reasoning, reducing parameters and improving throughput with minimal accuracy loss in both cloud and edge environments.

AI-generated summary

In this paper, we point out that the objective of the retrieval algorithms is to align with the LLM, which is similar to the objective of knowledge distillation in LLMs. We analyze the similarity in information focus between the distilled language model(DLM) and the original LLM from the perspective of information theory, and thus propose a novel paradigm that leverages a DLM as the retrieval algorithm. Based on the insight, we present SpeContext, an algorithm and system co-design for long-context reasoning. (1) At the algorithm level, SpeContext proposes lightweight retrieval head based on the head-level attention weights of DLM, achieving > 90% parameters reduction by pruning the redundancy. (2) At the system level, SpeContext designs an asynchronous prefetch dataflow via the elastic loading strategy, effectively overlapping KV cache retrieval with the LLM computation. (3) At the compilation level, SpeContext constructs the theoretical memory model and implements an adaptive memory management system to achieve acceleration by maximizing GPU memory utilization. We deploy and evaluate SpeContext in two resourceconstrained environments, cloud and edge. Extensive experiments show that, compared with the Huggingface framework, SpeContext achieves up to 24.89x throughput improvement in cloud and 10.06x speedup in edge with negligible accuracy loss, pushing the Pareto frontier of accuracy and throughput.

Community

Paper submitter

SpeContext accpeted by ASPLOS'26, which is the third paper in the Spec series (SpecEE [ISCA'25], SpecDiff [AAAI'25 Oral]). We apply speculative methods to sparse contexts and demonstrate from an information theory perspective that model distillation indirectly enables small models to learn the context importance focus of the original LLM. Therefore, we use the distilled small model to predict the important contexts of original LLM in advance. In resource-constrained cloud and edge scenarios, we have respectively achieved up to 22x throughput improvement and 10x speedup.

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2512.00722 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2512.00722 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2512.00722 in a Space README.md to link it from this page.

Collections including this paper 3