xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-24 03:14:28 +08:00
Code Issues Packages Projects Releases Wiki Activity
vllm/vllm/model_executor/models
History
jiahanc 34553b9d27
[Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next (#27492) 
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
2025-11-10 12:34:57 -05:00
..
transformers
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
__init__.py
[Chore] Remove SupportsV0Only interface and update supported models docs (#26783)
2025-10-14 04:55:10 -07:00
adapters.py
[Bugfix] Fix Qwen3-Reranker-8B load (#28117)
2025-11-05 18:33:50 +00:00
aimv2.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
apertus.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
arcee.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
arctic.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
aria.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
aya_vision.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
baichuan.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
bailing_moe.py
[Fix] Remove divisibility requirement between num_kv_heads and tp_size in bailing_moe (#26876)
2025-10-15 16:44:04 +08:00
bamba.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
bee.py
[Model][VLM] Support Bee-8B Model (#27012)
2025-10-20 02:31:26 +00:00
bert_with_rope.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
bert.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
blip2.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
blip.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
bloom.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
chameleon.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
chatglm.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
clip.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
cohere2_vision.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
commandr.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
config.py
[Performance][gpt-oss] Revert gpt-oss max cudagraph size to 1024 (#28345)
2025-11-08 15:50:10 -07:00
dbrx.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
deepencoder.py
[Model] Upstream Deepseek-OCR model (#27247)
2025-10-22 07:59:15 -07:00
deepseek_eagle.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
deepseek_mtp.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
deepseek_ocr.py
[Model] Consolidate Deepseek-MoE implementation with DeepSeek-v2 (#28101)
2025-11-08 05:01:27 +00:00
deepseek_v2.py
[RFC][ROCm][AITER] Keep all AITER kernels in _aiter_ops class like _custom_ops and _ipex_ops (#24490)
2025-11-10 08:20:53 -08:00
deepseek_vl2.py
[Model] Consolidate Deepseek-MoE implementation with DeepSeek-v2 (#28101)
2025-11-08 05:01:27 +00:00
dots1.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
dots_ocr.py
[Bugfix] Honor --mm_encoder_attn_backend when used (#27124)
2025-10-23 20:09:52 +08:00
ernie45_moe.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
ernie45_vl_moe.py
[Model][Bugfix] fix ernie45 vl run failed from shared experts optimization (#26885)
2025-10-16 03:37:35 -07:00
ernie45_vl.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
ernie45.py
[Model] Add PaddleOCR-VL Model Support (#27758)
2025-11-03 19:04:22 +08:00
ernie_mtp.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
exaone4.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
exaone.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
fairseq2_llama.py
…
falcon_h1.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
falcon.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
flex_olmo.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
fuyu.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
gemma2.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
gemma3_mm.py
[fix] Revert "fixing mm placeholder replacement issue with gemma3" (#28285)
2025-11-07 12:09:09 +00:00
gemma3.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
gemma3n_mm.py
Remove unused imports (#26972)
2025-10-16 19:51:17 -07:00
gemma3n.py
Fix hard-coded parameter name in gemma3n.py (#27946)
2025-11-05 23:07:36 -08:00
gemma.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
glm4_1v.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
glm4_moe_mtp.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
glm4_moe.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
glm4.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
glm4v.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
glm.py
…
gpt2.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
gpt_bigcode.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
gpt_j.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
gpt_neox.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
gpt_oss.py
[XPU] Add gpt-oss model support for Intel GPU (#27786)
2025-11-05 02:17:23 +00:00
granite_speech.py
[Model, Core] Support Granite Speech & LoRA for STT (#24455)
2025-11-05 08:33:48 +01:00
granite.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
granitemoe.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
granitemoehybrid.py
[Hybrid] Added supports_mamba_prefix_caching Protocol (#27339)
2025-10-27 13:05:20 +00:00
granitemoeshared.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
gritlm.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
grok1.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
h2ovl.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
hunyuan_v1.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
hyperclovax_vision.py
[Bugfix] Standardize merging multimodal embeddings (#26771)
2025-10-14 09:36:21 +00:00
idefics2_vision_model.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
idefics3.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
interfaces_base.py
[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)
2025-10-19 05:20:55 -07:00
interfaces.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
intern_vit.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
internlm2_ve.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
internlm2.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
interns1_vit.py
[Bugfix] Fix interns1-vit qk norm code path (#27480)
2025-10-24 17:43:45 +00:00
interns1.py
[Bugfix] Fix HF format InternVL large variants video processing (#27330)
2025-10-22 08:39:23 -07:00
internvl.py
[Chore] Clean up pytorch helper functions in vllm.utils (#26908)
2025-10-18 09:48:22 -07:00
jais.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
jamba.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
jina_vl.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
keye_vl1_5.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
keye.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
kimi_linear.py
fix incorrect type annotation in KimiMLP (#27885)
2025-10-31 17:38:02 +00:00
kimi_vl.py
[Chore] Clean up deepseek v2/v3 config copy (#28055)
2025-11-06 03:46:30 +00:00
lfm2_moe.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
lfm2.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
lightonocr.py
[Model] Add support for LightOnOCR (#26916)
2025-10-17 05:05:24 +00:00
llama4_eagle.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
llama4.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
llama_eagle3.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
llama_eagle.py
[Bugfix][Speculative Decoding] Extend Eagle quantization config fix to llama_eagle.py (#26590)
2025-10-13 17:17:13 +00:00
llama.py
Add llama 4 scaling support (#28145)
2025-11-06 18:55:17 +00:00
llava_next_video.py
[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)
2025-10-19 05:20:55 -07:00
llava_next.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
llava_onevision.py
[Bugfix] Standardize merging multimodal embeddings (#26771)
2025-10-14 09:36:21 +00:00
llava.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
longcat_flash_mtp.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
longcat_flash.py
[Misc] rename torch_dtype to dtype (#26695)
2025-10-15 12:11:48 +00:00
mamba2.py
[Hybrid] Added supports_mamba_prefix_caching Protocol (#27339)
2025-10-27 13:05:20 +00:00
mamba.py
[V1] [Hybrid] Mamba1 Automatic Prefix Caching (#26377)
2025-11-02 04:16:23 -08:00
medusa.py
…
midashenglm.py
[Model] Use merge_by_field_config for MM models (M-N) (#26710)
2025-10-14 01:27:01 +08:00
mimo_mtp.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
mimo.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
minicpm3.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
minicpm_eagle.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
minicpm.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
minicpmo.py
[Bugfix] Standardize merging multimodal embeddings (#26771)
2025-10-14 09:36:21 +00:00
minicpmv.py
[Quantization] Automatically infer AWQ modules_to_not_convert field (#26909)
2025-10-21 01:49:28 +00:00
minimax_m2.py
Fix MiniMax-M2 rmsnorm precision and remove useless code (#27627)
2025-10-29 21:01:05 +08:00
minimax_text_01.py
Remove unused imports (#26972)
2025-10-16 19:51:17 -07:00
minimax_vl_01.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
mistral3.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
mixtral.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
mllama4.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
mlp_speculator.py
…
modernbert.py
[Bugfix] Correct LayerNorm epsilon parameter in modernbert.py (#27008)
2025-10-16 12:27:44 +00:00
module_mapping.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
molmo.py
[Bugfix][Multi Modal] Fix incorrect Molmo token processing (#26873)
2025-10-15 07:13:59 +00:00
moonvit.py
[CI/Build] Bump transformers version (#27528)
2025-10-31 22:11:07 -07:00
mpt.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
nano_nemotron_vl.py
Nemotron Nano V2 VL + EVS Video Support (#27107)
2025-10-20 22:19:11 +08:00
nemotron_h.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
nemotron_nas.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
nemotron_vl.py
[Bugfix] Standardize merging multimodal embeddings (#26771)
2025-10-14 09:36:21 +00:00
nemotron.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
nvlm_d.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
olmo2.py
[Docs] Replace rst style double-backtick with md single-backtick (#27091)
2025-10-17 02:47:34 -07:00
olmo.py
[Docs] Replace rst style double-backtick with md single-backtick (#27091)
2025-10-17 02:47:34 -07:00
olmoe.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
openpangu_mtp.py
[model] Add support for openPangu_Ultra_MoE (#27521)
2025-11-04 08:17:20 -08:00
openpangu.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
opt.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
orion.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
ouro.py
[Model][Ouro] Support Ouro Model (#27794)
2025-10-30 22:34:41 +08:00
ovis2_5.py
[MM][Core] Decouple ViT backend from LM backend (#27061)
2025-10-21 00:30:10 -07:00
ovis.py
[Docs] Replace rst style double-backtick with md single-backtick (#27091)
2025-10-17 02:47:34 -07:00
paddleocr_vl.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
paligemma.py
[Model] Revert PR #26715: Restore custom PaliGemma and Gemma3-MM impl… (#27309)
2025-10-22 10:05:34 -07:00
persimmon.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
phi3.py
…
phi3v.py
[Model] Use merge_by_field_config for MM models (O-P) (#26776)
2025-10-14 09:42:45 +00:00
phi4_multimodal.py
[Model] Use merge_by_field_config for MM models (O-P) (#26776)
2025-10-14 09:42:45 +00:00
phi4mm_audio.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
phi4mm_utils.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
phi4mm.py
[Model] Use merge_by_field_config for MM models (O-P) (#26776)
2025-10-14 09:42:45 +00:00
phi.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
phimoe.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
pixtral.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
plamo2.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
qwen2_5_omni_thinker.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
qwen2_5_vl.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
qwen2_audio.py
[Model] Use merge_by_field_config for MM models (Qwen series) (#27546)
2025-10-27 05:38:05 +00:00
qwen2_moe.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
qwen2_rm.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
qwen2_vl.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
qwen2.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
qwen3_moe.py
[Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next (#27492)
2025-11-10 12:34:57 -05:00
qwen3_next_mtp.py
[BugFix] Support EP/DP + EPLB with MTP (#25311)
2025-11-05 15:22:17 +00:00
qwen3_next.py
[Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next (#27492)
2025-11-10 12:34:57 -05:00
qwen3_omni_moe_thinker.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
qwen3_vl_moe.py
[Model]Improve Qwen3VLMoeForConditionalGeneration packed_modules_mapping (#27096)
2025-10-17 04:47:00 -07:00
qwen3_vl.py
[V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395)
2025-11-11 00:30:06 +08:00
qwen3.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
qwen_vl.py
[Model] Use merge_by_field_config for MM models (Qwen series) (#27546)
2025-10-27 05:38:05 +00:00
qwen.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00
radio.py
Nemotron Nano V2 VL + EVS Video Support (#27107)
2025-10-20 22:19:11 +08:00
registry.py
[Model] Consolidate Deepseek-MoE implementation with DeepSeek-v2 (#28101)
2025-11-08 05:01:27 +00:00
roberta.py
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370)
2025-10-15 11:14:41 +00:00
rvl.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
seed_oss.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
siglip2navit.py
[Bugfix] Honor --mm_encoder_attn_backend when used (#27124)
2025-10-23 20:09:52 +08:00
siglip.py
[bugfix] fix siglip batch text output error (#28365)
2025-11-10 21:21:15 +08:00
skyworkr1v.py
[Model] Use merge_by_field_config for MM models (M-N) (#26710)
2025-10-14 01:27:01 +08:00
smolvlm.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
solar.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
stablelm.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
starcoder2.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
step3_text.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
step3_vl.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
swin.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
tarsier.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
telechat2.py
…
teleflm.py
…
terratorch.py
[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)
2025-10-23 14:46:18 +00:00
ultravox.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
utils.py
[V0 deprecation] Remove VLLM_USE_V1 usage in most modules (#27955)
2025-11-04 20:51:16 -08:00
vision.py
Fix issues from #28242 (#28257)
2025-11-07 04:23:17 +00:00
voxtral.py
Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
2025-10-12 09:51:31 -07:00
whisper.py
[Chore] Clean up pytorch helper functions in vllm.utils (#26908)
2025-10-18 09:48:22 -07:00
zamba2.py
[Misc][Model][Refactor] Pass the prefix into Linear layers (#28259)
2025-11-07 19:38:38 +08:00