3 people 5931b7e5d9 [Models][Quantization] Add quantization configuration update in Voxtral model (#24122) ...

Signed-off-by: Alexandre Marques <almarque@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2025-09-10 19:13:56 -07:00

..

__init__.py

[Core] Move multimodal placeholder from chat utils to model definition (#20355)

2025-07-03 08:18:30 +00:00

adapters.py

[Bugfix] Fix hidden_size for multimodal classification model (#24501)

2025-09-09 10:37:25 -07:00

aimv2.py

[Misc] Use config definitions from Transformers library (#21913)

2025-08-08 23:10:51 -07:00

apertus.py

Fix weights loading for Apertus (#24100)

2025-09-02 18:34:28 +00:00

arcee.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

arctic.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

aria.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

aya_vision.py

[Bugfix] Ensure correctness of Cohere2Vision processing (#23245)

2025-08-20 11:09:18 +00:00

baichuan.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

bailing_moe.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

bamba.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

bart.py

[New Model]mBART model (#22883)

2025-08-16 12:16:58 +00:00

bert_with_rope.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

bert.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

blip2.py

[Bugfix] Fix the issue that Blip2ForConditionalGeneration' object has… (#24028)

2025-09-02 11:54:20 +08:00

blip.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

bloom.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

chameleon.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

chatglm.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

clip.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

cohere2_vision.py

[CI/Build] Split out mm processor tests (#23260)

2025-08-20 20:05:20 -07:00

commandr.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

config.py

[New Model]: google/embeddinggemma-300m (#24318)

2025-09-05 22:58:36 -07:00

constant_size_cache.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

dbrx.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

deepseek_eagle.py

[Bugfix][Wide EP] Fix redundant work when using DeepEP, TP Attn, and EP MoE (#24134)

2025-09-08 19:01:51 -07:00

deepseek_mtp.py

[Bugfix][Wide EP] Fix redundant work when using DeepEP, TP Attn, and EP MoE (#24134)

2025-09-08 19:01:51 -07:00

deepseek_v2.py

[Bugfix][Wide EP] Fix redundant work when using DeepEP, TP Attn, and EP MoE (#24134)

2025-09-08 19:01:51 -07:00

deepseek_vl2.py

[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

2025-09-09 21:36:09 -07:00

deepseek.py

Add LoRA support for DeepSeek models (V2, V3, R1-0528) (#23971)

2025-08-30 06:40:02 -07:00

donut.py

Migrate DonutImagePixelInputs to TensorSchema (#23509)

2025-08-25 05:02:15 +00:00

dots1.py

[BugFix] Fix routed_scaling_factor double mul for dots1 and glm4 MoE models (#24132)

2025-09-03 04:57:59 +00:00

ernie45_moe.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

ernie45_vl_moe.py

[BugFix][Model] Fix Ernie4.5-VL hanging on long inputs (#24074)

2025-09-09 11:37:16 +08:00

ernie45_vl.py

[BugFix][Model] Fix Ernie4.5-VL hanging on long inputs (#24074)

2025-09-09 11:37:16 +08:00

ernie45.py

[Ernie 4.5] Name Change for Base 0.3B Model (#21735)

2025-07-28 12:22:32 +00:00

ernie_mtp.py

[Model][V1] Support Ernie MTP (#22169)

2025-08-20 20:41:55 +08:00

exaone4.py

[BugFix] Fix EXAONE4 rotary embeddings (#23918)

2025-09-02 14:40:55 +00:00

exaone.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

fairseq2_llama.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

falcon_h1.py

[V1] [Hybrid] Support using float32 for state in Hybrid Models (Mamba2, Mamba1, Minimax) (#22928)

2025-08-15 12:57:06 +00:00

falcon.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

florence2.py

[Bugfix] Fix broken Florence-2 model (#23426)

2025-08-22 17:50:52 +00:00

fuyu.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

gemma2.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

gemma3_mm.py

[Refactor] Pass tokenizer explicitly instead of binding to prompt update (#23542)

2025-08-25 06:31:57 -07:00

gemma3.py

[New Model]: google/embeddinggemma-300m (#24318)

2025-09-05 22:58:36 -07:00

gemma3n_mm.py

fix some typos (#24071)

2025-09-02 20:44:50 -07:00

gemma3n.py

Revert gemma3n fast prefill changes (#23897)

2025-08-29 12:16:57 -07:00

gemma.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

glm4_1v.py

[Model] Remove unnecessary CUDA sync of GLM-4.1V image and video preprocess (#24332)

2025-09-07 23:10:54 -07:00

glm4_moe_mtp.py

[Bugfix] Fix DeepSeek MTP (#22934)

2025-08-16 01:25:06 +00:00

glm4_moe.py

[Kernels] Overlap shared experts with send/recv (#23273)

2025-09-03 12:35:18 -04:00

glm4.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

glm4v.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

glm.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

gpt2.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

gpt_bigcode.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

gpt_j.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

gpt_neox.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

gpt_oss.py

[Model] [gpt-oss] fix gpt-oss pp support (#23815)

2025-08-28 05:36:55 -07:00

granite_speech.py

[CI/Build] Improve Tensor Schema tests speed by avoid engine core initialization (#23357)

2025-08-31 22:52:20 -07:00

granite.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

granitemoe.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

granitemoehybrid.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

granitemoeshared.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

gritlm.py

[V0 Deprecation] Remove pooling model support in V0 (#23434)

2025-08-29 00:04:02 -07:00

grok1.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

h2ovl.py

[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

2025-09-09 21:36:09 -07:00

hunyuan_v1.py

[Model] Add pp support for hunyuan (#24212)

2025-09-04 03:58:26 -07:00

hyperclovax_vision.py

[Core] Use key-only cache for BaseMultiModalProcessor (#23018)

2025-08-27 14:19:13 +08:00

idefics2_vision_model.py

Feature/vit attention unification# 23880 (#23978)

2025-09-10 06:10:14 -07:00

idefics3.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

interfaces_base.py

[Model] Explicit default_pooling_type interface (#23736)

2025-08-27 13:24:09 +00:00

interfaces.py

[Frontend] Gemma3n audio transcriptions/translations endpoint (#23735)

2025-09-01 18:07:46 +08:00

intern_vit.py

Feature/vit attention unification# 23880 (#23978)

2025-09-10 06:10:14 -07:00

internlm2_ve.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

internlm2.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

interns1_vit.py

Feature/vit attention unification# 23880 (#23978)

2025-09-10 06:10:14 -07:00

interns1.py

fix some typos (#24071)

2025-09-02 20:44:50 -07:00

internvl.py

[Model] Limit CPU threads for image transformations in InternVL to reduce cpu contention. (#24519)

2025-09-10 16:45:44 +08:00

jais.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

jamba.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

jina_vl.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

keye_vl1_5.py

[Model]: support KeyeVL-1_5-8B (#23838)

2025-09-01 03:50:27 -07:00

keye.py

[Model]: support KeyeVL-1_5-8B (#23838)

2025-09-01 03:50:27 -07:00

kimi_vl.py

[Model] Support DP for ViT on Kimi-VL-A3B-Thinking-2506 (#23817)

2025-09-01 16:56:56 +00:00

lfm2.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

llama4_eagle.py

[Meta] Official Eagle mm support, first enablement on llama4 (#20788)

2025-07-31 10:35:07 -07:00

llama4.py

[Kernels] Overlap shared experts with send/recv (#23273)

2025-09-03 12:35:18 -04:00

llama_eagle3.py

[BugFix][Spec Decode] Fix out-of-range index triggered by eagle3; re-enable test for LlamaForCausalLMEagle3 (#24392)

2025-09-09 21:24:23 -07:00

llama_eagle.py

[Meta] Official Eagle mm support, first enablement on llama4 (#20788)

2025-07-31 10:35:07 -07:00

llama.py

[Models][Quantization] Add quantization configuration update in Voxtral model (#24122)

2025-09-10 19:13:56 -07:00

llava_next_video.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

llava_next.py

Migrate LlavaNextImageInputs to TensorSchema (#21774)

2025-08-10 09:05:21 -07:00

llava_onevision.py

[Multimodal] Improve max video embedding length estimation in V1 (#24312)

2025-09-06 02:33:19 -07:00

llava.py

[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

2025-09-09 21:36:09 -07:00

mamba2.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

mamba_cache.py

[V1] [Hybrid] Support using float32 for state in Hybrid Models (Mamba2, Mamba1, Minimax) (#22928)

2025-08-15 12:57:06 +00:00

mamba.py

[V1][Mamba1] - Full CUDA and Piecewise CUDA Graphs Support (#23035)

2025-08-20 20:08:51 -07:00

medusa.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

midashenglm.py

[Model] Add MiDashengLM model support (#23652)

2025-09-04 00:08:09 -07:00

mimo_mtp.py

[Bugfix] Fix DeepSeek MTP (#22934)

2025-08-16 01:25:06 +00:00

mimo.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

minicpm3.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

minicpm_eagle.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

minicpm.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

minicpmo.py

Migrate MiniCPMOAudioInputs to TensorSchema (#21847)

2025-08-22 16:43:29 +08:00

minicpmv.py

[Model] Enable encoder DP for MiniCPM-V (#23948)

2025-08-30 06:31:26 -07:00

minimax_cache.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

minimax_text_01.py

[V1] [Hybrid] Move MiniMaxLinearAttention into layers/mamba (#23831)

2025-08-30 00:16:15 -07:00

minimax_vl_01.py

[Bugfix] Fix broken Minimax-01-VL model (#22116)

2025-08-19 08:49:29 +00:00

mistral3.py

[Core] Use key-only cache for BaseMultiModalProcessor (#23018)

2025-08-27 14:19:13 +08:00

mixtral.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

mllama4.py

Migrate Llama4ImagePatchInputs to TensorSchema (#22021)

2025-08-28 17:29:37 +00:00

mllama.py

Feature/vit attention unification# 23880 (#23978)

2025-09-10 06:10:14 -07:00

mlp_speculator.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

modernbert.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

module_mapping.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

molmo.py

[BugFix][Multi Modal] Fix TensorSchema shape mismatch in Molmo (#24559)

2025-09-10 06:14:27 -07:00

moonvit.py

[Model] Support DP for ViT on Kimi-VL-A3B-Thinking-2506 (#23817)

2025-09-01 16:56:56 +00:00

mpt.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

nano_nemotron_vl.py

Support for NemotronH Nano VLM (#23644)

2025-09-10 06:10:06 -07:00

nemotron_h.py

[Bugfix] fix modelopt exclude_modules name mapping (#24178)

2025-09-10 10:20:46 -07:00

nemotron_nas.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

nemotron_vl.py

Migrate InternVLImagePixelInputs (in nemotron_vl.py) to TensorSchema (#22023)

2025-08-19 13:48:26 +08:00

nemotron.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

nvlm_d.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

2025-08-18 09:52:00 +00:00

olmo2.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

olmo.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

olmoe.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

opt.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

orion.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

ovis2_5.py

[CI/Build] Improve Tensor Schema tests speed by avoid engine core initialization (#23357)

2025-08-31 22:52:20 -07:00

ovis.py

Migrate OvisImagePatchInputs to TensorSchema (#22024)

2025-09-02 12:01:36 +08:00

paligemma.py

[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

2025-09-09 21:36:09 -07:00

persimmon.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

phi3.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

phi3v.py

[Core] Use key-only cache for BaseMultiModalProcessor (#23018)

2025-08-27 14:19:13 +08:00

phi4_multimodal.py

Migrate Phi4 inputs to TensorSchema (#23471)

2025-09-01 14:05:59 +08:00

phi4flash.py

[BugFix] Fix regression caused by mamba state dtype PR (#22998)

2025-08-15 22:55:26 +00:00

phi4mm_audio.py

[Docs] Fix warnings in mkdocs build (continued) (#24092)

2025-09-10 06:23:28 -07:00

phi4mm_utils.py

[Docs] Fix warnings in mkdocs build (continued) (#24092)

2025-09-10 06:23:28 -07:00

phi4mm.py

Migrate Phi4 inputs to TensorSchema (#23471)

2025-09-01 14:05:59 +08:00

phi.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

phimoe.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

pixtral.py

[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

2025-09-09 21:36:09 -07:00

plamo2.py

[V1] v1 engine + full CUDA graph support for PLaMo2 (#23998)

2025-09-03 08:24:02 -07:00

qwen2_5_omni_thinker.py

[Model] Enable BNB support for qwen2_5_omni_thinker (#24420)

2025-09-08 09:37:08 -07:00

qwen2_5_vl.py

[Docs] Fix warnings in mkdocs build (continued) (#24092)

2025-09-10 06:23:28 -07:00

qwen2_audio.py

Migrate Qwen2 inputs to TensorSchema (#23475)

2025-09-06 20:07:31 -07:00

qwen2_moe.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

qwen2_rm.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

qwen2_vl.py

[Model] Remove unnecessary CUDA sync of Qwen2VL image and video preprocess (#24334)

2025-09-07 23:11:12 -07:00

qwen2.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

qwen3_moe.py

[BUGFIX] GPTQ quantization compatibility for Qwen3 MOE models (AutoGPTQ and AutoRound-GPTQ) (#23994)

2025-09-01 03:33:40 +00:00

qwen3.py

[mypy] Fix incorrect type hint for EAGLE3 support (#23617)

2025-08-25 23:50:17 -07:00

qwen_vl.py

Migrate Qwen inputs to TensorSchema (#23473)

2025-08-28 10:43:26 +08:00

qwen.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

registry.py

Support for NemotronH Nano VLM (#23644)

2025-09-10 06:10:06 -07:00

roberta.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

rvl.py

[Model][VLM] Support R-4B Model (#23246)

2025-08-21 04:08:52 +00:00

seed_oss.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

siglip2navit.py

[Model] Add Ovis2.5 PP support (#23405)

2025-08-22 17:46:34 +00:00

siglip.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

skyworkr1v.py

Migrate skyworkr1v inputs to TensorSchema (#23499)

2025-08-25 04:43:21 +00:00

smolvlm.py

[Misc] Automatically resolve HF processor init kwargs (#22005)

2025-07-31 22:44:10 -07:00

solar.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

stablelm.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

starcoder2.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

step3_text.py

[Models] Improve iteration over layers (#19497)

2025-08-29 09:26:34 +08:00

step3_vl.py

Feature/vit attention unification# 23880 (#23978)

2025-09-10 06:10:14 -07:00

swin.py

[New Model]Donut model (#23229)

2025-08-24 12:52:24 +00:00

tarsier.py

[Core] Use key-only cache for BaseMultiModalProcessor (#23018)

2025-08-27 14:19:13 +08:00

telechat2.py

[CI/Build] Fix registry tests (#21934)

2025-07-30 09:10:41 -07:00

teleflm.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

terratorch.py

[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

2025-09-09 21:36:09 -07:00

transformers.py

[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

2025-09-09 21:36:09 -07:00

ultravox.py

Migrate ultravox inputs to TensorSchema (#23503)

2025-09-04 06:09:11 +00:00

utils.py

[Bugfix] Fix hidden_size for multimodal classification model (#24501)

2025-09-09 10:37:25 -07:00

vision.py

Feature/vit attention unification# 23880 (#23978)

2025-09-10 06:10:14 -07:00

voxtral.py

[Models][Quantization] Add quantization configuration update in Voxtral model (#24122)

2025-09-10 19:13:56 -07:00

whisper.py

[v1] Add Whisper model support (encoder-decoder) (#21088)

2025-09-10 13:53:35 -07:00

zamba2.py

[Docs] Fix warnings in mkdocs build (continued) (#24092)

2025-09-10 06:23:28 -07:00