xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-02 02:57:53 +08:00
Code Issues Packages Projects Releases Wiki Activity
vllm/vllm/model_executor/models
History
Cyrus Leung 39b643dc1a
[Model] Use merge_by_field_config for MM models (G) (#26117) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-02 22:38:29 -07:00
..
__init__.py
[feat]: Create interface for model-specific M-RoPE (#24194)
2025-09-18 19:18:56 +00:00
adapters.py
Enable conversion of multimodal models to pooling tasks (#24451)
2025-09-12 03:30:41 +00:00
aimv2.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
apertus.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
arcee.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
arctic.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
aria.py
[Model] Use merge_by_field_config for MM models (A-C) (#26073)
2025-10-02 08:17:31 -07:00
aya_vision.py
[Model] Use merge_by_field_config for MM models (A-C) (#26073)
2025-10-02 08:17:31 -07:00
baichuan.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
bailing_moe.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
bamba.py
[V1] Remove V0 code paths for Hybrid models (#25400)
2025-09-23 08:26:13 -07:00
bert_with_rope.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
bert.py
[Bugfix] Token type and position embeddings fail to be applied to inputs_embeds (#25922)
2025-10-01 00:23:12 +08:00
blip2.py
[Model] Use merge_by_field_config for MM models (A-C) (#26073)
2025-10-02 08:17:31 -07:00
blip.py
[Misc] Add SPDX-FileCopyrightText (#19100)
2025-06-03 11:20:17 -07:00
bloom.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
chameleon.py
[Model] Use merge_by_field_config for MM models (A-C) (#26073)
2025-10-02 08:17:31 -07:00
chatglm.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
clip.py
[Model] Move vision_feature_select_strategy into resolve_visual_encoder_outputs (#25938)
2025-09-30 11:24:57 +00:00
cohere2_vision.py
[Model] Use merge_by_field_config for MM models (A-C) (#26073)
2025-10-02 08:17:31 -07:00
commandr.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
config.py
[BugFix] Fix default kv-cache-dtype default for DeepseekV3.2 (#25988)
2025-09-30 21:58:31 -07:00
dbrx.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
deepseek_eagle.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
deepseek_mtp.py
[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896)
2025-09-30 17:14:41 +08:00
deepseek_v2.py
[Deepseek v3.2] Support indexer prefill chunking (#25999)
2025-10-02 10:29:12 -07:00
deepseek_vl2.py
[Model] Use merge_by_field_config for MM models (D-F) (#26076)
2025-10-02 08:17:35 -07:00
deepseek.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
dots1.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
dots_ocr.py
[ROCm] [VL] [Bugfix] Fix vit flash attn dispatcher logic for ROCm (#26104)
2025-10-02 22:34:53 -07:00
ernie45_moe.py
[Bugfix][Model]fix ernie45 moe gate&bias dtype to float32 (#25936)
2025-09-30 19:11:21 +08:00
ernie45_vl_moe.py
[Bugfix][Model]fix ernie45 moe gate&bias dtype to float32 (#25936)
2025-09-30 19:11:21 +08:00
ernie45_vl.py
[ROCm] [VL] [Bugfix] Fix vit flash attn dispatcher logic for ROCm (#26104)
2025-10-02 22:34:53 -07:00
ernie45.py
[Ernie 4.5] Name Change for Base 0.3B Model (#21735)
2025-07-28 12:22:32 +00:00
ernie_mtp.py
[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982)
2025-09-27 14:22:28 +00:00
exaone4.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
exaone.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
fairseq2_llama.py
[Misc] Add SPDX-FileCopyrightText (#19100)
2025-06-03 11:20:17 -07:00
falcon_h1.py
[V1] Remove V0 code paths for Hybrid models (#25400)
2025-09-23 08:26:13 -07:00
falcon.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
fuyu.py
[Model] Use merge_by_field_config for MM models (D-F) (#26076)
2025-10-02 08:17:35 -07:00
gemma2.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
gemma3_mm.py
[Model] Use merge_by_field_config for MM models (G) (#26117)
2025-10-02 22:38:29 -07:00
gemma3.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
gemma3n_mm.py
[Model] Use merge_by_field_config for MM models (G) (#26117)
2025-10-02 22:38:29 -07:00
gemma3n.py
[KV sharing] Re-land Gemma3n model changes from #22628 (#24357)
2025-09-23 19:25:34 -07:00
gemma.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
glm4_1v.py
[Model] Use merge_by_field_config for MM models (G) (#26117)
2025-10-02 22:38:29 -07:00
glm4_moe_mtp.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
glm4_moe.py
Update GLM-4.5 Doc transformers version (#25830)
2025-09-28 12:05:51 +00:00
glm4.py
[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982)
2025-09-27 14:22:28 +00:00
glm4v.py
[Model] Use merge_by_field_config for MM models (G) (#26117)
2025-10-02 22:38:29 -07:00
glm.py
[Misc] Add SPDX-FileCopyrightText (#19100)
2025-06-03 11:20:17 -07:00
gpt2.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
gpt_bigcode.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
gpt_j.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
gpt_neox.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
gpt_oss.py
[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982)
2025-09-27 14:22:28 +00:00
granite_speech.py
[Model] Use merge_by_field_config for MM models (G) (#26117)
2025-10-02 22:38:29 -07:00
granite.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
granitemoe.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
granitemoehybrid.py
[V1] Remove V0 code paths for Hybrid models (#25400)
2025-09-23 08:26:13 -07:00
granitemoeshared.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
gritlm.py
[Misc] Simplify PoolerOutput and move to v1/outputs (#25629)
2025-09-25 06:47:03 +00:00
grok1.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
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
[Bugfix][Model] Fix inference for Hunyuan dense models (#25354)
2025-09-30 14:38:07 +00:00
hyperclovax_vision.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
idefics2_vision_model.py
[Misc] Move DP for ViT code inside model executor dir (#25459)
2025-09-23 09:20:52 +00:00
idefics3.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
interfaces_base.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
interfaces.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
intern_vit.py
[Misc] Move DP for ViT code inside model executor dir (#25459)
2025-09-23 09:20:52 +00:00
internlm2_ve.py
[Models] Improve iteration over layers (#19497)
2025-08-29 09:26:34 +08:00
internlm2.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
interns1_vit.py
Feature/vit attention unification# 23880 (#23978)
2025-09-10 06:10:14 -07:00
interns1.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
internvl.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
jais.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
jamba.py
[V1] Remove V0 code paths for Hybrid models (#25400)
2025-09-23 08:26:13 -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
[Docs] Fix warnings in mkdocs build (continued) (#24791)
2025-09-13 00:13:44 -07:00
keye.py
[Attention] Move Backend enum into registry (#25893)
2025-10-02 20:32:24 -07:00
kimi_vl.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
lfm2.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
llama4_eagle.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
llama4.py
[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982)
2025-09-27 14:22:28 +00:00
llama_eagle3.py
[Bugfix][Speculative Decoding] Fix Eagle3 quantization config issue (#25883)
2025-09-29 11:37:20 -04:00
llama_eagle.py
[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982)
2025-09-27 14:22:28 +00:00
llama.py
[Bugfix][Speculative Decoding] Fix Eagle3 quantization config issue (#25883)
2025-09-29 11:37:20 -04:00
llava_next_video.py
[Model] Move vision_feature_select_strategy into resolve_visual_encoder_outputs (#25938)
2025-09-30 11:24:57 +00:00
llava_next.py
[Misc] Factor out common _apply_feature_select_strategy (#26003)
2025-10-01 01:31:03 -07:00
llava_onevision.py
[Model] Move vision_feature_select_strategy into resolve_visual_encoder_outputs (#25938)
2025-09-30 11:24:57 +00:00
llava.py
[Misc] Factor out common _apply_feature_select_strategy (#26003)
2025-10-01 01:31:03 -07:00
longcat_flash_mtp.py
[Model] Add LongCat-Flash (#23991)
2025-09-24 21:53:40 -07:00
longcat_flash.py
[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896)
2025-09-30 17:14:41 +08:00
mamba2.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
mamba.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
medusa.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
midashenglm.py
[Model][Bugfix] Fix MiDashengLM audio encoder mask by removing incorrect logical_not (#25925)
2025-09-30 08:15:23 +00:00
mimo_mtp.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
mimo.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
minicpm3.py
[Misc] Add SPDX-FileCopyrightText (#19100)
2025-06-03 11:20:17 -07:00
minicpm_eagle.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
minicpm.py
Eagle3 that supports the Minicpm3 model (#24243)
2025-09-26 10:04:57 -07:00
minicpmo.py
[Quantization] Add field to skip unquantized modules for GPTQ config (#25455)
2025-09-26 15:47:41 +00:00
minicpmv.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
minimax_text_01.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
minimax_vl_01.py
[Model] Move vision_feature_select_strategy into resolve_visual_encoder_outputs (#25938)
2025-09-30 11:24:57 +00:00
mistral3.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
mixtral.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
mllama4.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
mlp_speculator.py
[V0 Deprecation] Remove V0 Sequence class & Sampler (#25332)
2025-09-21 08:52:15 -07:00
modernbert.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
module_mapping.py
[Misc] Add SPDX-FileCopyrightText (#19100)
2025-06-03 11:20:17 -07:00
molmo.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
moonvit.py
[Docs] Fix warnings in mkdocs build (continued) (#24791)
2025-09-13 00:13:44 -07:00
mpt.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
nano_nemotron_vl.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
nemotron_h.py
[V1] Remove V0 code paths for Hybrid models (#25400)
2025-09-23 08:26:13 -07:00
nemotron_nas.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
nemotron_vl.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
nemotron.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
nvlm_d.py
[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)
2025-08-18 09:52:00 +00:00
olmo2.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
olmo.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
olmoe.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
opt.py
Test Prompt Embeds/LoRA compatibility and Enable LoRA Support for OPT Models (#25717)
2025-09-30 08:10:58 +08:00
orion.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
ovis2_5.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
ovis.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
paligemma.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
persimmon.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
phi3.py
[Misc] Add SPDX-FileCopyrightText (#19100)
2025-06-03 11:20:17 -07:00
phi3v.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
phi4_multimodal.py
[Misc] Remove more get_input_embeddings_v0 (#25857)
2025-09-29 08:03:37 +00:00
phi4mm_audio.py
[Doc]: fixing doc typos (#24635)
2025-09-10 23:19:28 -07:00
phi4mm_utils.py
[Docs] Fix warnings in mkdocs build (continued) (#24092)
2025-09-10 06:23:28 -07:00
phi4mm.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
phi.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
phimoe.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
pixtral.py
[Model] Move vision_feature_select_strategy into resolve_visual_encoder_outputs (#25938)
2025-09-30 11:24:57 +00:00
plamo2.py
[Kernel] Chunk-aligned mamba2 (#24683)
2025-09-29 23:18:25 +02:00
qwen2_5_omni_thinker.py
[BugFix][MM] Fix Nonetype error when video is cache in qwen2.5-omni-thinker (#26004)
2025-10-01 08:03:25 +00:00
qwen2_5_vl.py
[ROCm] [VL] [Bugfix] Fix vit flash attn dispatcher logic for ROCm (#26104)
2025-10-02 22:34:53 -07:00
qwen2_audio.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
qwen2_moe.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
qwen2_rm.py
[Model] Systematic support for fp32 head, pooling models part (#23810)
2025-09-09 07:29:50 -07:00
qwen2_vl.py
[ROCm] [VL] [Bugfix] Fix vit flash attn dispatcher logic for ROCm (#26104)
2025-10-02 22:34:53 -07:00
qwen2.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
qwen3_moe.py
[Bugfix] Fix Qwen3-VL regression from #24982 (#25814)
2025-09-28 03:21:09 +00:00
qwen3_next_mtp.py
[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982)
2025-09-27 14:22:28 +00:00
qwen3_next.py
[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982)
2025-09-27 14:22:28 +00:00
qwen3_vl_moe.py
[MM] Add text-only mode for Qwen3-VL (#26000)
2025-09-30 21:13:42 -07:00
qwen3_vl.py
[ROCm] [VL] [Bugfix] Fix vit flash attn dispatcher logic for ROCm (#26104)
2025-10-02 22:34:53 -07:00
qwen3.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
qwen_vl.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
qwen.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
radio.py
Add RADIO Vision Encoder Support to vLLM (#24595)
2025-09-17 05:53:30 -07:00
registry.py
Add explicit pooling classes for the Transformers backend (#25322)
2025-09-30 23:07:06 +01:00
roberta.py
[Bugfix] Token type and position embeddings fail to be applied to inputs_embeds (#25922)
2025-10-01 00:23:12 +08:00
rvl.py
[Model][VLM] Support R-4B Model (#23246)
2025-08-21 04:08:52 +00:00
seed_oss.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
siglip2navit.py
[ROCm] [VL] [Bugfix] Fix vit flash attn dispatcher logic for ROCm (#26104)
2025-10-02 22:34:53 -07:00
siglip.py
[Model] Move vision_feature_select_strategy into resolve_visual_encoder_outputs (#25938)
2025-09-30 11:24:57 +00:00
skyworkr1v.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
smolvlm.py
[Misc] Automatically resolve HF processor init kwargs (#22005)
2025-07-31 22:44:10 -07:00
solar.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
stablelm.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
starcoder2.py
[V0 Deprecation] Remove V0 sampling metadata (#25345)
2025-09-21 10:37:11 -07:00
step3_text.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
step3_vl.py
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
swin.py
[New Model]Donut model (#23229)
2025-08-24 12:52:24 +00:00
tarsier.py
[Misc] Factor out common _apply_feature_select_strategy (#26003)
2025-10-01 01:31:03 -07:00
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
[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
2025-09-27 08:15:12 +00:00
transformers_pooling.py
Add explicit pooling classes for the Transformers backend (#25322)
2025-09-30 23:07:06 +01:00
transformers.py
Update to Transformers v4.56.2 (#24638)
2025-09-30 22:07:07 -07:00
ultravox.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
utils.py
[Misc] Remove more get_input_embeddings_v0 (#25857)
2025-09-29 08:03:37 +00:00
vision.py
[Attention] Move Backend enum into registry (#25893)
2025-10-02 20:32:24 -07:00
voxtral.py
[V0 Deprecation][Models] Remove all V0 condition for mm embeddings merge (#25331)
2025-09-29 14:09:18 +08:00
whisper.py
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
2025-09-29 19:49:49 -07:00
zamba2.py
[Docs] Enable fail_on_warning for the docs build in CI (#25580)
2025-09-24 19:30:33 +00:00