vLLM/vllm/model_executor/models at a869baca73eb90ae7bd18402915dc4bfc36cf06b - vLLM

__init__.py

[V1]SupportsV0Only protocol for model definitions (#13959 )

2025-02-27 20:02:15 -05:00

adapters.py

[Bugfix] Fix missing return value in load_weights method of adapters.py (#15542 )

2025-03-31 06:56:42 -07:00

aimv2.py

[Model] Broadcast Ovis2 implementation to fit Ovis1.6 (#17861 )

2025-05-11 17:56:30 -07:00

arctic.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

aria.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

aya_vision.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

baichuan.py

[Bugfix][Model] Fix baichuan model loader for tp (#18597 )

2025-05-23 02:39:05 -07:00

bamba.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

bart.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

bert_with_rope.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

bert.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

blip2.py

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

blip.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

bloom.py

[Model] use AutoWeightsLoader for bloom (#18300 )

2025-05-20 09:40:05 -07:00

chameleon.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

chatglm.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

clip.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

commandr.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

constant_size_cache.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

dbrx.py

[Model] Use autoweightloader for dbrx (#18251 )

2025-05-16 07:54:13 -07:00

deepseek_mtp.py

[V1] Support Deepseek MTP (#18435 )

2025-05-23 10:26:28 -07:00

deepseek_v2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

deepseek_vl2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

deepseek.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

eagle.py

[Spec Decode][V0] Fix spec decode correctness test in V0 eagle/medusa (#18175 )

2025-05-18 19:49:46 -07:00

exaone.py

[Bugfix] config.head_dim is now explicitly set to None (#18432 )

2025-05-20 21:04:33 -07:00

fairseq2_llama.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

falcon_h1.py

[FalconH1] Fix output dtype in RMSNorm fallback path for Falcon-H1 (e.g. 0.5B) (#18500 )

2025-05-21 19:23:59 -07:00

falcon.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

florence2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

fuyu.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

gemma2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

gemma3_mm.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

gemma3.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

gemma.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

glm4.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

glm4v.py

[VLM] Avoid unnecessary dummy multimodal data during processing (#16416 )

2025-04-10 19:32:14 +00:00

glm.py

[Bugfix] Fix GLM rotary_dim issue and support v1 (#16912 )

2025-04-21 14:26:34 +00:00

gpt2.py

[Model] use AutoWeightsLoader for gpt2 (#18625 )

2025-05-24 13:36:13 +00:00

gpt_bigcode.py

[Bugfix] Fix the lm_head in gpt_bigcode in lora mode (#6357 )

2025-05-26 14:52:25 +08:00

gpt_j.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

gpt_neox.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

granite_speech.py

fix: typos (#18151 )

2025-05-15 02:16:15 -07:00

granite.py

[Bugfix] config.head_dim is now explicitly set to None (#18432 )

2025-05-20 21:04:33 -07:00

granitemoe.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

granitemoehybrid.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

granitemoeshared.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

gritlm.py

[Model] GritLM supports other attention backends (#18109 )

2025-05-14 03:33:19 -07:00

grok1.py

[CI] Enable test_initialization to run on V1 (#16736 )

2025-05-23 15:09:44 -07:00

h2ovl.py

[VLM] Initialize video input support for InternVL models (#18499 )

2025-05-25 04:51:25 +00:00

idefics2_vision_model.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

idefics3.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

interfaces_base.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

interfaces.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

intern_vit.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

internlm2_ve.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

internlm2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

internvl.py

[VLM] Initialize video input support for InternVL models (#18499 )

2025-05-25 04:51:25 +00:00

jais.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

jamba.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

kimi_vl.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

llama4.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

llama_eagle3.py

[Spec Decode] Make EAGLE3 draft token ID mapping optional (#18488 )

2025-05-22 20:17:39 -07:00

llama_eagle.py

[V1][Spec Decoding] Use model_loader.get_model() to load models (#18273 )

2025-05-23 02:05:44 +00:00

llama.py

[Bugfix] Fix Llama GGUF initialization (#18717 )

2025-05-26 07:49:22 -07:00

llava_next_video.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

llava_next.py

Replace {func} with mkdocs style links (#18610 )

2025-05-23 05:51:38 -07:00

llava_onevision.py

[Bugfix] Inconsistent token calculation compared to HF in llava family (#18479 )

2025-05-21 20:21:47 -07:00

llava.py

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

mamba2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

mamba_cache.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

mamba.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

medusa.py

[V1][Spec Decoding] Use model_loader.get_model() to load models (#18273 )

2025-05-23 02:05:44 +00:00

mimo_mtp.py

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454 )

2025-05-23 16:16:26 -07:00

mimo.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

minicpm3.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

minicpm.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

minicpmo.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

minicpmv.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

minimax_cache.py

[Model][MiniMaxText01] Support MiniMaxText01 model inference (#13454 )

2025-04-01 16:23:55 -04:00

minimax_text_01.py

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454 )

2025-05-23 16:16:26 -07:00

minimax_vl_01.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

mistral3.py

Migrate docs from Sphinx to MkDocs (#18145 )

2025-05-23 02:09:53 -07:00

mixtral_quant.py

[Bugfix] config.head_dim is now explicitly set to None (#18432 )

2025-05-20 21:04:33 -07:00

mixtral.py

[Bugfix] config.head_dim is now explicitly set to None (#18432 )

2025-05-20 21:04:33 -07:00

mllama4.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

mllama.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

mlp_speculator.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

modernbert.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

module_mapping.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

molmo.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

moonvit.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

mpt.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

nemotron_nas.py

[Model] Add support for YARN in NemotronNAS models (#18427 )

2025-05-26 10:31:49 +00:00

nemotron.py

[Bugfix] config.head_dim is now explicitly set to None (#18432 )

2025-05-20 21:04:33 -07:00

nvlm_d.py

[VLM] Initialize video input support for InternVL models (#18499 )

2025-05-25 04:51:25 +00:00

olmo2.py

[Bugfix][Model] Make Olmo2Model weight loading return loaded weights (#18504 )

2025-05-21 21:17:03 -07:00

olmo.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

olmoe.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

opt.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

orion.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

ovis.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

paligemma.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

persimmon.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

phi3_small.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

phi3.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628 )

2025-02-02 11:58:18 -08:00

phi3v.py

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454 )

2025-05-23 16:16:26 -07:00

phi4mm_audio.py

fix: typos (#18151 )

2025-05-15 02:16:15 -07:00

phi4mm_utils.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

phi4mm.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

phi.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

phimoe.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

pixtral.py

[Bugfix] Fix profiling dummy data for Pixtral (#18677 )

2025-05-25 14:05:30 +00:00

plamo2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

prithvi_geospatial_mae.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

qwen2_5_omni_thinker.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

qwen2_5_vl.py

[PERF] Speed up Qwen2.5-VL model by speed up rotary position embedding (#17973 )

2025-05-15 23:31:02 -07:00

qwen2_audio.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

qwen2_moe.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

qwen2_rm.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

qwen2_vl.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

qwen2.py

[Model] Allow the use of sliding window in Qwen2 (#17772 )

2025-05-14 22:29:38 -07:00

qwen3_moe.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

qwen3.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

qwen_vl.py

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454 )

2025-05-23 16:16:26 -07:00

qwen.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

registry.py

[Model] Add support for Qwen2.5-Omni-7B-AWQ (Qwen2_5OmniForConditionalGeneration) (#18647 )

2025-05-24 09:15:36 +00:00

roberta.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

siglip.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

skyworkr1v.py

Re-submit: Fix: Proper RGBA -> RGB conversion for PIL images. (#18569 )

2025-05-23 01:59:18 +00:00

smolvlm.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

solar.py

[Bugfix] config.head_dim is now explicitly set to None (#18432 )

2025-05-20 21:04:33 -07:00

stablelm.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

starcoder2.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

telechat2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

teleflm.py

Upstream Llama4 Support to Main (#16113 )

2025-04-07 08:06:27 -07:00

transformers.py

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454 )

2025-05-23 16:16:26 -07:00

ultravox.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

utils.py

[Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358 )

2025-05-19 20:20:12 -07:00

vision.py

Fix PixtralHF missing spatial_merge_size (#17571 )

2025-05-01 22:14:09 -07:00

whisper.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00

zamba2.py

Update deprecated type hinting in models (#18132 )

2025-05-14 22:06:50 -07:00