Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+8a7b90c915c1cecaf381c70594e3f955.edf filter=lfs diff=lfs merge=lfs -text
+97bb3cab5f2f7f5f4640c04cbf3b6ee0.edf filter=lfs diff=lfs merge=lfs -text
+9ad47915b97d47d3ce069c00271807d6.edf filter=lfs diff=lfs merge=lfs -text
+eb1a559cd1f53e2ede74f1307030a1d0.edf filter=lfs diff=lfs merge=lfs -text
+92713480ca8937ba5a8dadead5278d92.edf filter=lfs diff=lfs merge=lfs -text
+0ff335c7ce60753ee28a910e9fab16f4.edf filter=lfs diff=lfs merge=lfs -text

0ff335c7ce60753ee28a910e9fab16f4.edf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb70ff6f1027da1e8384576d0fd2f8726a58067c3e21c551fee8c2289df412e0
+size 1222930525

8a7b90c915c1cecaf381c70594e3f955.edf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a6e3c4b25a50829662d10233901fbaeb610770b244d2d780743b8cc2effef5
+size 1215314627

92713480ca8937ba5a8dadead5278d92.edf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb498ec1cb2a29aa3a9951b57031dcf5813010a78ee5b764ba57308679e0a7cc
+size 1218953632

97bb3cab5f2f7f5f4640c04cbf3b6ee0.edf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33c01d1653a010f4b2f90d69a7e6f25791efcd8101ac9d1c089890a252d1f45
+size 1223602936

9ad47915b97d47d3ce069c00271807d6.edf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1268b4add4f2602bdc8f941d2f049f6258b3e377dcc7aa12e8383ac2eefdc2bd
+size 1219094832

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,38 @@
+---
+base_model: google-bert/bert-large-uncased
+license: apache-2.0
+pipeline_tag: question-answering
+library_name: furiosa-llm
+tags:
+  - furiosa-ai
+---
+# Model Overview
+- **Model Architecture:** Bert
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+- **Maximum Context Length:** 384 tokens
+- **Intended Use Cases:** Intended for commercial and non-commercial use. Same as [google/bert-large-uncase](https://huggingface.co/google-bert/bert-large-uncased), this models is intended for question-answering.
+- **Release Date:** 04/12/2025
+- **Version:** v2025.2
+- **License(s):** [Apache License 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)
+- **Supported Inference Engine(s):** Furiosa LLM
+- **Supported Hardware Compatibility:** FuriosaAI RNGD
+- **Preferred Operating System(s):** Linux
+- **Quantization:**
+  - Tool: Furiosa Model Compressor v0.6.2, included in Furiosa SDK 2025.2
+  - Weight: int8, Activation: int8, KV cache: int8
+  - Calibration: [SQuAD v1.1 dataset](https://rajpurkar.github.io/SQuAD-explorer/) ([instruction](https://zenodo.org/records/4792496)), [100 samples](https://github.com/mlcommons/inference/blob/master/calibration/SQuAD-v1.1/bert_calibration_features.txt)
+
+
+## Description:
+This model is the pre-compiled version of the [google/bert-large-uncase](https://huggingface.co/google-bert/bert-large-uncased), which is an embedding model that uses an optimized transformer architecture.
+
+## Usage
+
+### MLPerf Benchmark using RNGD
+Follow the example command below after [installing furiosa-mlperf and its prerequisites](https://developer.furiosa.ai/latest/en/getting_started/furiosa_mlperf.html).
+
+```sh
+furiosa-mlperf bert-offline furiosa-ai/bert-large-uncased-INT8-MLPerf ./mlperf-result
+```

artifact.json

@@ -0,0 +1,1581 @@
+{
+  "metadata": {
+    "artifact_id": "d86d900b-d7f7-4838-9727-35ca1b0d4ec4",
+    "name": "mlperf-bert",
+    "timestamp": 1745456449,
+    "furiosa_llm_version": "249c6f1",
+    "furiosa_compiler_version": "b504d5d48"
+  },
+  "model": {
+    "generator_config": {
+      "position_id_pad": 1,
+      "buckets": [
+        {
+          "batch_size": 1,
+          "attention_size": 384,
+          "kv_cache_size": 0
+        },
+        {
+          "batch_size": 1,
+          "attention_size": 320,
+          "kv_cache_size": 0
+        },
+        {
+          "batch_size": 1,
+          "attention_size": 192,
+          "kv_cache_size": 0
+        },
+        {
+          "batch_size": 1,
+          "attention_size": 128,
+          "kv_cache_size": 0
+        },
+        {
+          "batch_size": 1,
+          "attention_size": 160,
+          "kv_cache_size": 0
+        },
+        {
+          "batch_size": 2,
+          "attention_size": 96,
+          "kv_cache_size": 0
+        }
+      ],
+      "model_qname": "furiosa_llm_models.bert.symbolic.mlperf_submission.BertForQuestionAnswering",
+      "paged_attention_config": null,
+      "packing_type": "IDENTITY",
+      "kv_cache_sharing_across_beams_config": null,
+      "num_speculative_tokens": null,
+      "unpadded_vocab_size": null
+    },
+    "hf_config": {
+      "return_dict": true,
+      "output_hidden_states": false,
+      "output_attentions": false,
+      "torchscript": false,
+      "torch_dtype": "float32",
+      "use_bfloat16": false,
+      "tf_legacy_loss": false,
+      "pruned_heads": {},
+      "tie_word_embeddings": true,
+      "chunk_size_feed_forward": 0,
+      "is_encoder_decoder": false,
+      "is_decoder": false,
+      "cross_attention_hidden_size": null,
+      "add_cross_attention": false,
+      "tie_encoder_decoder": false,
+      "max_length": 20,
+      "min_length": 0,
+      "do_sample": false,
+      "early_stopping": false,
+      "num_beams": 1,
+      "num_beam_groups": 1,
+      "diversity_penalty": 0.0,
+      "temperature": 1.0,
+      "top_k": 50,
+      "top_p": 1.0,
+      "typical_p": 1.0,
+      "repetition_penalty": 1.0,
+      "length_penalty": 1.0,
+      "no_repeat_ngram_size": 0,
+      "encoder_no_repeat_ngram_size": 0,
+      "bad_words_ids": null,
+      "num_return_sequences": 1,
+      "output_scores": false,
+      "return_dict_in_generate": false,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "remove_invalid_values": false,
+      "exponential_decay_length_penalty": null,
+      "suppress_tokens": null,
+      "begin_suppress_tokens": null,
+      "architectures": [
+        "BertForQuestionAnswering"
+      ],
+      "finetuning_task": null,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "tokenizer_class": null,
+      "prefix": null,
+      "bos_token_id": null,
+      "pad_token_id": 0,
+      "eos_token_id": null,
+      "sep_token_id": null,
+      "decoder_start_token_id": null,
+      "task_specific_params": null,
+      "problem_type": null,
+      "_name_or_path": "furiosa-ai/mlperf-bert-large",
+      "_attn_implementation_autoset": false,
+      "transformers_version": "4.48.1",
+      "model_type": "bert",
+      "vocab_size": 30522,
+      "hidden_size": 1024,
+      "num_hidden_layers": 24,
+      "num_attention_heads": 16,
+      "hidden_act": "rngd_gelu",
+      "intermediate_size": 4096,
+      "hidden_dropout_prob": 0.1,
+      "attention_probs_dropout_prob": 0.1,
+      "max_position_embeddings": 512,
+      "type_vocab_size": 2,
+      "initializer_range": 0.02,
+      "layer_norm_eps": 1e-12,
+      "position_embedding_type": "absolute",
+      "use_cache": true,
+      "classifier_dropout": null
+    },
+    "model_metadata": {
+      "pretrained_id": "furiosa-ai/mlperf-bert-large",
+      "task_type": "question-answering",
+      "llm_config": {
+        "optimization_config": {
+          "attention_type": "VANILLA",
+          "optimize_rope": false,
+          "optimize_packed": false,
+          "decompose_layernorm": false,
+          "optimize_furiosa": false,
+          "use_unsplit_packed": true,
+          "compact_causal_mask": false,
+          "use_rngd_gelu": true,
+          "causal_mask_free_decoding": false,
+          "kv_cache_sharing_across_beams": false,
+          "inbound_beamsearch_softmax": false,
+          "calculate_logit_only_for_last_token": false,
+          "optimized_for_speculative_decoding": false
+        },
+        "quantization_config": {
+          "weight": "int8",
+          "activation": "int8",
+          "kv_cache": "int8",
+          "use_mcp": true
+        }
+      },
+      "hf_configs": {},
+      "model_weight_path": null,
+      "trust_remote_code": null,
+      "allow_bfloat16_cast_with_mcp": true,
+      "auto_bfloat16_cast": null
+    },
+    "model_rewriting_config": {
+      "do_decompositions_for_model_rewrite": false,
+      "use_blockwise_compile": true,
+      "embedding_layer_as_single_block": false,
+      "num_blocks_per_supertask": 24,
+      "embed_all_constants_into_graph": true,
+      "optimize_logit_shape": true
+    },
+    "parallel_config": {
+      "tensor_parallel_size": 1,
+      "pipeline_parallel_size": 1
+    },
+    "pipelines": [
+      {
+        "name": "Quantized_furiosa_llm_models.bert.symbolic.mlperf_submission.BertForQuestionAnswering-kv0-b1-attn384",
+        "devices": {
+          "0": "npu:0:0"
+        },
+        "tensors": {
+          "d0_arg0_1": {
+            "shape": [
+              1,
+              384
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg1_1": {
+            "shape": [
+              1,
+              384
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg2_1": {
+            "shape": [
+              1,
+              384,
+              384
+            ],
+            "dtype": "bool"
+          },
+          "d0_arg3_1": {
+            "shape": [
+              1,
+              384
+            ],
+            "dtype": "i32"
+          },
+          "submod_d0_c0": {
+            "shape": [
+              1,
+              384,
+              2
+            ],
+            "dtype": "f32"
+          }
+        },
+        "supertasks": {
+          "0": {
+            "kind": "input",
+            "inputs": [],
+            "outputs": [
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg2_1",
+              "d0_arg3_1"
+            ]
+          },
+          "1": {
+            "kind": "output",
+            "inputs": [
+              "submod_d0_c0"
+            ],
+            "outputs": []
+          },
+          "2": {
+            "kind": "edf",
+            "inputs": [
+              "d0_arg2_1",
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg3_1"
+            ],
+            "outputs": [
+              "submod_d0_c0"
+            ],
+            "device": "0",
+            "data": null,
+            "data_blob": "92713480ca8937ba5a8dadead5278d92"
+          }
+        },
+        "metadata": {
+          "tensors": {
+            "inputs": {
+              "input_ids": {
+                "shape": [
+                  1,
+                  384
+                ],
+                "dtype": "i32",
+                "idx": 0
+              },
+              "token_type_ids": {
+                "shape": [
+                  1,
+                  384
+                ],
+                "dtype": "i32",
+                "idx": 1
+              },
+              "attention_mask": {
+                "shape": [
+                  1,
+                  384,
+                  384
+                ],
+                "dtype": "bool",
+                "idx": 2
+              },
+              "position_ids": {
+                "shape": [
+                  1,
+                  384
+                ],
+                "dtype": "i32",
+                "idx": 3
+              }
+            },
+            "outputs": {
+              "logits": {
+                "shape": [
+                  1,
+                  384,
+                  2
+                ],
+                "dtype": "f32",
+                "idx": 0
+              }
+            }
+          },
+          "tensor_slices": {
+            "inputs": {
+              "d0_arg0_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    384
+                  ]
+                ],
+                "origin": "input_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg1_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    384
+                  ]
+                ],
+                "origin": "token_type_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg2_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    384
+                  ],
+                  [
+                    0,
+                    384
+                  ]
+                ],
+                "origin": "attention_mask",
+                "dtype": "bool",
+                "device": "0"
+              },
+              "d0_arg3_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    384
+                  ]
+                ],
+                "origin": "position_ids",
+                "dtype": "i32",
+                "device": "0"
+              }
+            },
+            "outputs": {
+              "submod_d0_c0": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    384
+                  ],
+                  [
+                    0,
+                    2
+                  ]
+                ],
+                "origin": "logits",
+                "dtype": "f32",
+                "device": "0"
+              }
+            }
+          }
+        },
+        "blobs": {
+          "92713480ca8937ba5a8dadead5278d92": null
+        },
+        "param_files": {
+          "0": {
+            "path": "params-mlperf-bert-large-mlperf_submission-24L-W8A8KV8-allow_bfloat16_cast_with_mcp-ba480aa7f239d5bf87fdd9b369ce396c7f516f5fcecf3f40000671d6299f6f5c.safetensors",
+            "format": "safetensors"
+          }
+        },
+        "device_constraints": [],
+        "version": "0.1.0"
+      },
+      {
+        "name": "Quantized_furiosa_llm_models.bert.symbolic.mlperf_submission.BertForQuestionAnswering-kv0-b1-attn320",
+        "devices": {
+          "0": "npu:0:0"
+        },
+        "tensors": {
+          "d0_arg0_1": {
+            "shape": [
+              1,
+              320
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg1_1": {
+            "shape": [
+              1,
+              320
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg2_1": {
+            "shape": [
+              1,
+              320,
+              320
+            ],
+            "dtype": "bool"
+          },
+          "d0_arg3_1": {
+            "shape": [
+              1,
+              320
+            ],
+            "dtype": "i32"
+          },
+          "submod_d0_c0": {
+            "shape": [
+              1,
+              320,
+              2
+            ],
+            "dtype": "f32"
+          }
+        },
+        "supertasks": {
+          "0": {
+            "kind": "input",
+            "inputs": [],
+            "outputs": [
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg2_1",
+              "d0_arg3_1"
+            ]
+          },
+          "1": {
+            "kind": "output",
+            "inputs": [
+              "submod_d0_c0"
+            ],
+            "outputs": []
+          },
+          "2": {
+            "kind": "edf",
+            "inputs": [
+              "d0_arg2_1",
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg3_1"
+            ],
+            "outputs": [
+              "submod_d0_c0"
+            ],
+            "device": "0",
+            "data": null,
+            "data_blob": "0ff335c7ce60753ee28a910e9fab16f4"
+          }
+        },
+        "metadata": {
+          "tensors": {
+            "inputs": {
+              "input_ids": {
+                "shape": [
+                  1,
+                  320
+                ],
+                "dtype": "i32",
+                "idx": 0
+              },
+              "token_type_ids": {
+                "shape": [
+                  1,
+                  320
+                ],
+                "dtype": "i32",
+                "idx": 1
+              },
+              "attention_mask": {
+                "shape": [
+                  1,
+                  320,
+                  320
+                ],
+                "dtype": "bool",
+                "idx": 2
+              },
+              "position_ids": {
+                "shape": [
+                  1,
+                  320
+                ],
+                "dtype": "i32",
+                "idx": 3
+              }
+            },
+            "outputs": {
+              "logits": {
+                "shape": [
+                  1,
+                  320,
+                  2
+                ],
+                "dtype": "f32",
+                "idx": 0
+              }
+            }
+          },
+          "tensor_slices": {
+            "inputs": {
+              "d0_arg0_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    320
+                  ]
+                ],
+                "origin": "input_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg1_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    320
+                  ]
+                ],
+                "origin": "token_type_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg2_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    320
+                  ],
+                  [
+                    0,
+                    320
+                  ]
+                ],
+                "origin": "attention_mask",
+                "dtype": "bool",
+                "device": "0"
+              },
+              "d0_arg3_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    320
+                  ]
+                ],
+                "origin": "position_ids",
+                "dtype": "i32",
+                "device": "0"
+              }
+            },
+            "outputs": {
+              "submod_d0_c0": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    320
+                  ],
+                  [
+                    0,
+                    2
+                  ]
+                ],
+                "origin": "logits",
+                "dtype": "f32",
+                "device": "0"
+              }
+            }
+          }
+        },
+        "blobs": {
+          "0ff335c7ce60753ee28a910e9fab16f4": null
+        },
+        "param_files": {
+          "0": {
+            "path": "params-mlperf-bert-large-mlperf_submission-24L-W8A8KV8-allow_bfloat16_cast_with_mcp-ba480aa7f239d5bf87fdd9b369ce396c7f516f5fcecf3f40000671d6299f6f5c.safetensors",
+            "format": "safetensors"
+          }
+        },
+        "device_constraints": [],
+        "version": "0.1.0"
+      },
+      {
+        "name": "Quantized_furiosa_llm_models.bert.symbolic.mlperf_submission.BertForQuestionAnswering-kv0-b1-attn192",
+        "devices": {
+          "0": "npu:0:0"
+        },
+        "tensors": {
+          "d0_arg0_1": {
+            "shape": [
+              1,
+              192
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg1_1": {
+            "shape": [
+              1,
+              192
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg2_1": {
+            "shape": [
+              1,
+              192,
+              192
+            ],
+            "dtype": "bool"
+          },
+          "d0_arg3_1": {
+            "shape": [
+              1,
+              192
+            ],
+            "dtype": "i32"
+          },
+          "submod_d0_c0": {
+            "shape": [
+              1,
+              192,
+              2
+            ],
+            "dtype": "f32"
+          }
+        },
+        "supertasks": {
+          "0": {
+            "kind": "input",
+            "inputs": [],
+            "outputs": [
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg2_1",
+              "d0_arg3_1"
+            ]
+          },
+          "1": {
+            "kind": "output",
+            "inputs": [
+              "submod_d0_c0"
+            ],
+            "outputs": []
+          },
+          "2": {
+            "kind": "edf",
+            "inputs": [
+              "d0_arg2_1",
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg3_1"
+            ],
+            "outputs": [
+              "submod_d0_c0"
+            ],
+            "device": "0",
+            "data": null,
+            "data_blob": "eb1a559cd1f53e2ede74f1307030a1d0"
+          }
+        },
+        "metadata": {
+          "tensors": {
+            "inputs": {
+              "input_ids": {
+                "shape": [
+                  1,
+                  192
+                ],
+                "dtype": "i32",
+                "idx": 0
+              },
+              "token_type_ids": {
+                "shape": [
+                  1,
+                  192
+                ],
+                "dtype": "i32",
+                "idx": 1
+              },
+              "attention_mask": {
+                "shape": [
+                  1,
+                  192,
+                  192
+                ],
+                "dtype": "bool",
+                "idx": 2
+              },
+              "position_ids": {
+                "shape": [
+                  1,
+                  192
+                ],
+                "dtype": "i32",
+                "idx": 3
+              }
+            },
+            "outputs": {
+              "logits": {
+                "shape": [
+                  1,
+                  192,
+                  2
+                ],
+                "dtype": "f32",
+                "idx": 0
+              }
+            }
+          },
+          "tensor_slices": {
+            "inputs": {
+              "d0_arg0_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    192
+                  ]
+                ],
+                "origin": "input_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg1_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    192
+                  ]
+                ],
+                "origin": "token_type_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg2_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    192
+                  ],
+                  [
+                    0,
+                    192
+                  ]
+                ],
+                "origin": "attention_mask",
+                "dtype": "bool",
+                "device": "0"
+              },
+              "d0_arg3_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    192
+                  ]
+                ],
+                "origin": "position_ids",
+                "dtype": "i32",
+                "device": "0"
+              }
+            },
+            "outputs": {
+              "submod_d0_c0": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    192
+                  ],
+                  [
+                    0,
+                    2
+                  ]
+                ],
+                "origin": "logits",
+                "dtype": "f32",
+                "device": "0"
+              }
+            }
+          }
+        },
+        "blobs": {
+          "eb1a559cd1f53e2ede74f1307030a1d0": null
+        },
+        "param_files": {
+          "0": {
+            "path": "params-mlperf-bert-large-mlperf_submission-24L-W8A8KV8-allow_bfloat16_cast_with_mcp-ba480aa7f239d5bf87fdd9b369ce396c7f516f5fcecf3f40000671d6299f6f5c.safetensors",
+            "format": "safetensors"
+          }
+        },
+        "device_constraints": [],
+        "version": "0.1.0"
+      },
+      {
+        "name": "Quantized_furiosa_llm_models.bert.symbolic.mlperf_submission.BertForQuestionAnswering-kv0-b1-attn128",
+        "devices": {
+          "0": "npu:0:0"
+        },
+        "tensors": {
+          "d0_arg0_1": {
+            "shape": [
+              1,
+              128
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg1_1": {
+            "shape": [
+              1,
+              128
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg2_1": {
+            "shape": [
+              1,
+              128,
+              128
+            ],
+            "dtype": "bool"
+          },
+          "d0_arg3_1": {
+            "shape": [
+              1,
+              128
+            ],
+            "dtype": "i32"
+          },
+          "submod_d0_c0": {
+            "shape": [
+              1,
+              128,
+              2
+            ],
+            "dtype": "f32"
+          }
+        },
+        "supertasks": {
+          "0": {
+            "kind": "input",
+            "inputs": [],
+            "outputs": [
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg2_1",
+              "d0_arg3_1"
+            ]
+          },
+          "1": {
+            "kind": "output",
+            "inputs": [
+              "submod_d0_c0"
+            ],
+            "outputs": []
+          },
+          "2": {
+            "kind": "edf",
+            "inputs": [
+              "d0_arg2_1",
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg3_1"
+            ],
+            "outputs": [
+              "submod_d0_c0"
+            ],
+            "device": "0",
+            "data": null,
+            "data_blob": "9ad47915b97d47d3ce069c00271807d6"
+          }
+        },
+        "metadata": {
+          "tensors": {
+            "inputs": {
+              "input_ids": {
+                "shape": [
+                  1,
+                  128
+                ],
+                "dtype": "i32",
+                "idx": 0
+              },
+              "token_type_ids": {
+                "shape": [
+                  1,
+                  128
+                ],
+                "dtype": "i32",
+                "idx": 1
+              },
+              "attention_mask": {
+                "shape": [
+                  1,
+                  128,
+                  128
+                ],
+                "dtype": "bool",
+                "idx": 2
+              },
+              "position_ids": {
+                "shape": [
+                  1,
+                  128
+                ],
+                "dtype": "i32",
+                "idx": 3
+              }
+            },
+            "outputs": {
+              "logits": {
+                "shape": [
+                  1,
+                  128,
+                  2
+                ],
+                "dtype": "f32",
+                "idx": 0
+              }
+            }
+          },
+          "tensor_slices": {
+            "inputs": {
+              "d0_arg0_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    128
+                  ]
+                ],
+                "origin": "input_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg1_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    128
+                  ]
+                ],
+                "origin": "token_type_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg2_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    128
+                  ],
+                  [
+                    0,
+                    128
+                  ]
+                ],
+                "origin": "attention_mask",
+                "dtype": "bool",
+                "device": "0"
+              },
+              "d0_arg3_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    128
+                  ]
+                ],
+                "origin": "position_ids",
+                "dtype": "i32",
+                "device": "0"
+              }
+            },
+            "outputs": {
+              "submod_d0_c0": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    128
+                  ],
+                  [
+                    0,
+                    2
+                  ]
+                ],
+                "origin": "logits",
+                "dtype": "f32",
+                "device": "0"
+              }
+            }
+          }
+        },
+        "blobs": {
+          "9ad47915b97d47d3ce069c00271807d6": null
+        },
+        "param_files": {
+          "0": {
+            "path": "params-mlperf-bert-large-mlperf_submission-24L-W8A8KV8-allow_bfloat16_cast_with_mcp-ba480aa7f239d5bf87fdd9b369ce396c7f516f5fcecf3f40000671d6299f6f5c.safetensors",
+            "format": "safetensors"
+          }
+        },
+        "device_constraints": [],
+        "version": "0.1.0"
+      },
+      {
+        "name": "Quantized_furiosa_llm_models.bert.symbolic.mlperf_submission.BertForQuestionAnswering-kv0-b1-attn160",
+        "devices": {
+          "0": "npu:0:0"
+        },
+        "tensors": {
+          "d0_arg0_1": {
+            "shape": [
+              1,
+              160
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg1_1": {
+            "shape": [
+              1,
+              160
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg2_1": {
+            "shape": [
+              1,
+              160,
+              160
+            ],
+            "dtype": "bool"
+          },
+          "d0_arg3_1": {
+            "shape": [
+              1,
+              160
+            ],
+            "dtype": "i32"
+          },
+          "submod_d0_c0": {
+            "shape": [
+              1,
+              160,
+              2
+            ],
+            "dtype": "f32"
+          }
+        },
+        "supertasks": {
+          "0": {
+            "kind": "input",
+            "inputs": [],
+            "outputs": [
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg2_1",
+              "d0_arg3_1"
+            ]
+          },
+          "1": {
+            "kind": "output",
+            "inputs": [
+              "submod_d0_c0"
+            ],
+            "outputs": []
+          },
+          "2": {
+            "kind": "edf",
+            "inputs": [
+              "d0_arg2_1",
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg3_1"
+            ],
+            "outputs": [
+              "submod_d0_c0"
+            ],
+            "device": "0",
+            "data": null,
+            "data_blob": "8a7b90c915c1cecaf381c70594e3f955"
+          }
+        },
+        "metadata": {
+          "tensors": {
+            "inputs": {
+              "input_ids": {
+                "shape": [
+                  1,
+                  160
+                ],
+                "dtype": "i32",
+                "idx": 0
+              },
+              "token_type_ids": {
+                "shape": [
+                  1,
+                  160
+                ],
+                "dtype": "i32",
+                "idx": 1
+              },
+              "attention_mask": {
+                "shape": [
+                  1,
+                  160,
+                  160
+                ],
+                "dtype": "bool",
+                "idx": 2
+              },
+              "position_ids": {
+                "shape": [
+                  1,
+                  160
+                ],
+                "dtype": "i32",
+                "idx": 3
+              }
+            },
+            "outputs": {
+              "logits": {
+                "shape": [
+                  1,
+                  160,
+                  2
+                ],
+                "dtype": "f32",
+                "idx": 0
+              }
+            }
+          },
+          "tensor_slices": {
+            "inputs": {
+              "d0_arg0_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    160
+                  ]
+                ],
+                "origin": "input_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg1_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    160
+                  ]
+                ],
+                "origin": "token_type_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg2_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    160
+                  ],
+                  [
+                    0,
+                    160
+                  ]
+                ],
+                "origin": "attention_mask",
+                "dtype": "bool",
+                "device": "0"
+              },
+              "d0_arg3_1": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    160
+                  ]
+                ],
+                "origin": "position_ids",
+                "dtype": "i32",
+                "device": "0"
+              }
+            },
+            "outputs": {
+              "submod_d0_c0": {
+                "placements": [
+                  [
+                    0,
+                    1
+                  ],
+                  [
+                    0,
+                    160
+                  ],
+                  [
+                    0,
+                    2
+                  ]
+                ],
+                "origin": "logits",
+                "dtype": "f32",
+                "device": "0"
+              }
+            }
+          }
+        },
+        "blobs": {
+          "8a7b90c915c1cecaf381c70594e3f955": null
+        },
+        "param_files": {
+          "0": {
+            "path": "params-mlperf-bert-large-mlperf_submission-24L-W8A8KV8-allow_bfloat16_cast_with_mcp-ba480aa7f239d5bf87fdd9b369ce396c7f516f5fcecf3f40000671d6299f6f5c.safetensors",
+            "format": "safetensors"
+          }
+        },
+        "device_constraints": [],
+        "version": "0.1.0"
+      },
+      {
+        "name": "Quantized_furiosa_llm_models.bert.symbolic.mlperf_submission.BertForQuestionAnswering-kv0-b2-attn96",
+        "devices": {
+          "0": "npu:0:0"
+        },
+        "tensors": {
+          "d0_arg0_1": {
+            "shape": [
+              2,
+              96
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg1_1": {
+            "shape": [
+              2,
+              96
+            ],
+            "dtype": "i32"
+          },
+          "d0_arg2_1": {
+            "shape": [
+              2,
+              96,
+              96
+            ],
+            "dtype": "bool"
+          },
+          "d0_arg3_1": {
+            "shape": [
+              2,
+              96
+            ],
+            "dtype": "i32"
+          },
+          "submod_d0_c0": {
+            "shape": [
+              2,
+              96,
+              2
+            ],
+            "dtype": "f32"
+          }
+        },
+        "supertasks": {
+          "0": {
+            "kind": "input",
+            "inputs": [],
+            "outputs": [
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg2_1",
+              "d0_arg3_1"
+            ]
+          },
+          "1": {
+            "kind": "output",
+            "inputs": [
+              "submod_d0_c0"
+            ],
+            "outputs": []
+          },
+          "2": {
+            "kind": "edf",
+            "inputs": [
+              "d0_arg2_1",
+              "d0_arg0_1",
+              "d0_arg1_1",
+              "d0_arg3_1"
+            ],
+            "outputs": [
+              "submod_d0_c0"
+            ],
+            "device": "0",
+            "data": null,
+            "data_blob": "97bb3cab5f2f7f5f4640c04cbf3b6ee0"
+          }
+        },
+        "metadata": {
+          "tensors": {
+            "inputs": {
+              "input_ids": {
+                "shape": [
+                  2,
+                  96
+                ],
+                "dtype": "i32",
+                "idx": 0
+              },
+              "token_type_ids": {
+                "shape": [
+                  2,
+                  96
+                ],
+                "dtype": "i32",
+                "idx": 1
+              },
+              "attention_mask": {
+                "shape": [
+                  2,
+                  96,
+                  96
+                ],
+                "dtype": "bool",
+                "idx": 2
+              },
+              "position_ids": {
+                "shape": [
+                  2,
+                  96
+                ],
+                "dtype": "i32",
+                "idx": 3
+              }
+            },
+            "outputs": {
+              "logits": {
+                "shape": [
+                  2,
+                  96,
+                  2
+                ],
+                "dtype": "f32",
+                "idx": 0
+              }
+            }
+          },
+          "tensor_slices": {
+            "inputs": {
+              "d0_arg0_1": {
+                "placements": [
+                  [
+                    0,
+                    2
+                  ],
+                  [
+                    0,
+                    96
+                  ]
+                ],
+                "origin": "input_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg1_1": {
+                "placements": [
+                  [
+                    0,
+                    2
+                  ],
+                  [
+                    0,
+                    96
+                  ]
+                ],
+                "origin": "token_type_ids",
+                "dtype": "i32",
+                "device": "0"
+              },
+              "d0_arg2_1": {
+                "placements": [
+                  [
+                    0,
+                    2
+                  ],
+                  [
+                    0,
+                    96
+                  ],
+                  [
+                    0,
+                    96
+                  ]
+                ],
+                "origin": "attention_mask",
+                "dtype": "bool",
+                "device": "0"
+              },
+              "d0_arg3_1": {
+                "placements": [
+                  [
+                    0,
+                    2
+                  ],
+                  [
+                    0,
+                    96
+                  ]
+                ],
+                "origin": "position_ids",
+                "dtype": "i32",
+                "device": "0"
+              }
+            },
+            "outputs": {
+              "submod_d0_c0": {
+                "placements": [
+                  [
+                    0,
+                    2
+                  ],
+                  [
+                    0,
+                    96
+                  ],
+                  [
+                    0,
+                    2
+                  ]
+                ],
+                "origin": "logits",
+                "dtype": "f32",
+                "device": "0"
+              }
+            }
+          }
+        },
+        "blobs": {
+          "97bb3cab5f2f7f5f4640c04cbf3b6ee0": null
+        },
+        "param_files": {
+          "0": {
+            "path": "params-mlperf-bert-large-mlperf_submission-24L-W8A8KV8-allow_bfloat16_cast_with_mcp-ba480aa7f239d5bf87fdd9b369ce396c7f516f5fcecf3f40000671d6299f6f5c.safetensors",
+            "format": "safetensors"
+          }
+        },
+        "device_constraints": [],
+        "version": "0.1.0"
+      }
+    ],
+    "pipeline_metadata_list": [
+      {
+        "output_logits_size": null
+      },
+      {
+        "output_logits_size": null
+      },
+      {
+        "output_logits_size": null
+      },
+      {
+        "output_logits_size": null
+      },
+      {
+        "output_logits_size": null
+      },
+      {
+        "output_logits_size": null
+      }
+    ],
+    "max_prompt_len": null
+  },
+  "speculative_model": null,
+  "version": {
+    "major": 2,
+    "minor": 0
+  },
+  "prefill_chunk_size": null
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "furiosa-ai/mlperf-bert-large",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "rngd_gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eb1a559cd1f53e2ede74f1307030a1d0.edf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c953d6374b6a56db9f8e0814b91fdd6e45e7db740ec66b907e0d40eab5673586
+size 1219702748

furiosa_config.json

@@ -0,0 +1,56 @@
+{
+  "config_version": "1.0.0",
+  "model_id": "furiosa-ai/mlperf-bert-large",
+  "model_kinds": [
+    "ARTIFACT"
+  ],
+  "model_class": {
+    "module": "furiosa_llm_models.bert.symbolic.mlperf_submission",
+    "name": "BertForQuestionAnswering"
+  },
+  "llm_config": {
+    "optimization_config": {
+      "attention_type": "VANILLA",
+      "optimize_rope": false,
+      "optimize_packed": false,
+      "decompose_layernorm": false,
+      "optimize_furiosa": false,
+      "use_unsplit_packed": true,
+      "compact_causal_mask": false,
+      "use_rngd_gelu": true,
+      "causal_mask_free_decoding": false,
+      "kv_cache_sharing_across_beams": false,
+      "inbound_beamsearch_softmax": false,
+      "calculate_logit_only_for_last_token": false,
+      "optimized_for_speculative_decoding": false
+    },
+    "quantization_config": {
+      "weight": "int8",
+      "activation": "int8",
+      "kv_cache": "int8",
+      "use_mcp": true
+    }
+  },
+  "components_versions": {
+    "furiosa_llm": {
+      "version": "0.1.0-dev",
+      "git_hash": "249c6f1",
+      "build_time": null
+    },
+    "furiosa_ir": {
+      "version": "0.11.0-dev",
+      "git_hash": "c5be5877b",
+      "build_time": "2025-04-23T22:34:58Z"
+    },
+    "furiosa_runtime": {
+      "version": "2025.2.0",
+      "git_hash": "3ba9de71e",
+      "build_time": "2025-04-23T22:39:37Z"
+    },
+    "furiosa_model_compressor": {
+      "version": "2025.2.0 (rev: e4565f6)",
+      "git_hash": null,
+      "build_time": null
+    }
+  }
+}

params-mlperf-bert-large-mlperf_submission-24L-W8A8KV8-allow_bfloat16_cast_with_mcp-ba480aa7f239d5bf87fdd9b369ce396c7f516f5fcecf3f40000671d6299f6f5c.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ca766ce22770cdec44e351b9250d1af405e4aa1b6861fe8e93cf7067e17a00c
+size 369541408

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}