iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
27ec8ac626345498fdac0527a4fcd1451c24bebc
vLLM/vllm/model_executor/models
T
History
Lucas WilkinsonOpenAI CodexClaude Opus 5
 72aedcc426 [DCP] Default query replication for GLM sparse attention (#50382) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-21 09:07:05 -07:00
..
transformers
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
__init__.py
[Bugfix][Model Runner V2] Restore multimodal draft capability detection (#50417)
2026-08-03 14:18:14 -07:00
adapters.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
afmoe.py
[Refactor] Delete dead code in models (#51838)
2026-08-11 15:44:26 -04:00
aimv2.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
apertus.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
arcee.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
arctic.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
aria.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
audioflamingo3.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
AXK1.py
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
2026-08-18 12:56:56 -04:00
bagel.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
bailing_moe_linear.py
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[aA][bB]" (#48977)
2026-08-06 19:30:15 +00:00
bailing_moe_mtp.py
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[aA][bB]" (#48977)
2026-08-06 19:30:15 +00:00
bailing_moe_v3_mtp.py
[Model] [Quantization] Add Ling hybrid MXFP4 routed experts support (#52114)
2026-08-13 21:46:53 +08:00
bailing_moe_v3.py
[Model] [Quantization] Add Ling hybrid MXFP4 routed experts support (#52114)
2026-08-13 21:46:53 +08:00
bailing_moe.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
bee.py
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[aA][bB]" (#48977)
2026-08-06 19:30:15 +00:00
bert_with_rope.py
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[aA][bB]" (#48977)
2026-08-06 19:30:15 +00:00
bert.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
blip2.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
blip.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
bloom.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
chameleon.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
chatglm.py
Remove unnecessary load_weights methods (#44589)
2026-06-29 01:52:23 -07:00
cheers.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
clip.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
cohere2_moe.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
cohere2_vision.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
cohere_asr.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
cohere_eagle.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
colbert.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
colmodernvbert.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
colpali.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
colqwen3_5.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
colqwen3.py
[EPD] Allow KV consumers to omit MM embeddings (#52697)
2026-08-19 02:16:08 +00:00
commandr.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
config.py
[DCP] Default query replication for GLM sparse attention (#50382)
2026-08-21 09:07:05 -07:00
conformer_encoder.py
…
cosmos3_edge.py
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[cC][dD]" (#52003)
2026-08-13 11:33:55 +08:00
cosmos3.py
Cosmos3 FP8 ModelOpt/Diffusers remapping (#48952)
2026-07-20 11:31:48 -07:00
dbrx.py
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[cC][dD]" (#52003)
2026-08-13 11:33:55 +08:00
deepencoder2.py
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[cC][dD]" (#52003)
2026-08-13 11:33:55 +08:00
deepencoder.py
[Mypy Fix] Mypy fix for "vllm/model_executor/models/[cC][dD]" (#52003)
2026-08-13 11:33:55 +08:00
deepseek_eagle3.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
deepseek_eagle.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
deepseek_mtp.py
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
2026-08-18 12:56:56 -04:00
deepseek_ocr2.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
deepseek_ocr.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
deepseek_v2.py
[DCP] Default query replication for GLM sparse attention (#50382)
2026-08-21 09:07:05 -07:00
deepseek_vl2.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
diffusion_gemma.py
[Platform] Fill in the missing backend parameter for torch.compile (#51781)
2026-08-19 10:31:19 +00:00
dots_ocr.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
eagle2_5_vl.py
…
ernie45_moe.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
ernie45_vl_moe.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
ernie45_vl.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
ernie45.py
…
ernie_mtp.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
exaone4_5_mtp.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
exaone4_5.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
exaone4.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
exaone_moe_mtp.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
exaone_moe.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
exaone.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
extract_hidden_states.py
[Spec Decode] Fix hidden-state extraction block size for hybrid verifiers (#46301)
2026-06-30 08:19:51 -07:00
fairseq2_llama.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
falcon_h1.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
falcon.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
fireredasr2.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
fireredlid.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
flex_olmo.py
[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)
2026-07-31 11:28:18 +01:00
funasr.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
funaudiochat.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
gemma2.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
gemma3_mm.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
gemma3.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
gemma3n_audio_utils.py
…
gemma3n_mm.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
gemma3n.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
gemma4_dspark.py
Fix Gemma 4 for upcoming Transformers version (#49797)
2026-08-10 07:48:26 +00:00
gemma4_mm.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
gemma4_mtp.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
gemma4_unified.py
[Bugfix][Model] Gemma3n/Gemma4: pad variable-length audio batches (#50958)
2026-08-05 12:46:00 +08:00
gemma4.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
gemma.py
[Bugfix] Load untied Gemma LM head weights (#53170)
2026-08-21 00:47:08 +00:00
glm4_1v.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
glm4_moe_lite_mtp.py
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
2026-08-18 12:56:56 -04:00
glm4_moe_lite.py
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
2026-08-18 12:56:56 -04:00
glm4_moe_mtp.py
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
2026-08-18 12:56:56 -04:00
glm4_moe.py
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
2026-08-18 12:56:56 -04:00
glm4.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
glm4v.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
glm_ocr_mtp.py
Remove even more unnecessary load_weights methods (#48496)
2026-07-18 08:40:27 +00:00
glm_ocr.py
[Refactor] Remove multiple dead codes (#50285)
2026-08-03 10:59:08 -04:00
glm.py
…
glmasr_utils.py
…
glmasr.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
gpt2.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
gpt_j.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
gpt_neox.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
gpt_oss.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
granite4_vision.py
[MM] Keep more metadata tensors on CPU (#52827)
2026-08-18 19:56:33 -07:00
granite_speech_plus.py
Add model support for granite speech plus (#43519)
2026-06-04 14:47:48 +00:00
granite_speech.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
granite.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
granitemoe.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
granitemoehybrid.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
granitemoeshared.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
gritlm.py
…
h2ovl.py
[Model] Remove Mono-InternVL (InternLM2VEForCausalLM) (#45129)
2026-06-12 10:41:09 +00:00
hrm_text.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
hunyuan_v1.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
hunyuan_vision.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
hy_v3_mtp.py
Remove even more unnecessary load_weights methods (#48496)
2026-07-18 08:40:27 +00:00
hy_v3.py
[Bugfix] Fix HYV3 shared_mlp prefix for compressed-tensors ignore matching (#48682)
2026-08-21 09:07:01 -07:00
hyperclovax_vision_v2.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
hyperclovax_vision.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
hyperclovax.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
idefics2_vision_model.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
idefics3.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
interfaces_base.py
…
interfaces.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
intern_vit.py
Remove even more unnecessary load_weights methods (#48496)
2026-07-18 08:40:27 +00:00
internlm2.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
interns1_pro.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
interns1_vit.py
Remove even more unnecessary load_weights methods (#48496)
2026-07-18 08:40:27 +00:00
interns1.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
interns2_mobius.py
[Bugfix][Refactor] Keep Qwen3Next layer boundaries sequence parallel (#50685)
2026-08-14 11:58:32 +08:00
interns2_preview.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
internvl.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
iquest_loopcoder.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
isaac.py
[BugFix] Revert incorrect MM keep_on_cpu=True changes (#52881)
2026-08-19 07:07:40 +00:00
jais2.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
jamba.py
[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)
2026-07-31 11:28:18 +01:00
jina_vl.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
jina.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
kanana_v.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
keye_vl1_5.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
keye.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
kimi_audio.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
kimi_k25_vit.py
[Kernel][Kimi] fused vision q/k roper kernel (#50400)
2026-08-20 09:15:47 +00:00
kimi_k25.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
kimi_vl.py
[MM] Keep more metadata tensors on CPU (#52827)
2026-08-18 19:56:33 -07:00
laguna_dflash.py
Add Laguna XS.2.1 DFlash drafter support (#46853)
2026-07-02 18:09:27 -07:00
laguna.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
lfm2_moe.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
lfm2_siglip2.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
lfm2_vl.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
lfm2.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
lightonocr.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
llama4_eagle.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
llama4.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
llama_eagle3.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
llama_eagle.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
llama.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
llava_next_video.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
llava_next.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
llava_onevision2.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
llava_onevision.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
llava.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
longcat_flash_mtp.py
[Model] Add LongCat-Flash-Lite (n-gram embedding) (#47857)
2026-07-10 07:17:50 -07:00
longcat_flash_ngram.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
longcat_flash.py
[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)
2026-07-31 11:28:18 +01:00
mamba2.py
Remove unnecessary load_weights methods (#44589)
2026-06-29 01:52:23 -07:00
mamba.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
medusa.py
Add Medusa speculative decoding e2e test (#41396)
2026-06-30 18:02:22 +00:00
mellum.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
midashenglm.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
mimo_audio.py
[Model] Add MiMo-V2.5 support (#40967)
2026-04-27 13:26:51 +00:00
mimo_mtp.py
Remove more unnecessary load_weights methods (#47058)
2026-06-30 15:22:16 +01:00
mimo_v2_mtp.py
[SpecDecoding] extend mtp support for mimo 2.5 (#41905)
2026-05-09 18:22:59 +00:00
mimo_v2_omni.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
mimo_v2.py
[Refactor] Delete dead code in models (#51838)
2026-08-11 15:44:26 -04:00
mimo.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
minicpm3.py
[Perf] RMSNorm uncontiguous support, 1.2~3.1x kernel performance improvement (#49750)
2026-07-29 13:45:38 -07:00
minicpm_eagle.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
minicpm.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
minicpmo.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
minicpmv4_6.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
minicpmv.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
minimax_m2.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
mistral3.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
mistral_eagle.py
[Bugfix][Model Runner V2] Restore multimodal draft capability detection (#50417)
2026-08-03 14:18:14 -07:00
mistral_large_3_eagle.py
[Bugfix][Model Runner V2] Restore multimodal draft capability detection (#50417)
2026-08-03 14:18:14 -07:00
mistral_large_3.py
[Model] Migrate MistralLarge3ForCausalLM to AutoWeightsLoader (#48153)
2026-07-10 12:27:58 +00:00
mistral.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
mixtral.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
mllama4.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
mlp_speculator.py
…
modernbert.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
module_mapping.py
…
molmo2.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
molmo.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
moondream3.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
moonvit.py
[Core] Check for GPU<->CPU syncs during CI (#43107)
2026-08-14 17:42:05 -07:00
moss_audio.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
moss_transcribe_diarize.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
mpt.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
muse_glimmer.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
nano_nemotron_vl.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
nemotron_h_mtp.py
fix: ensure no double load of lm head in nemotron mtp (#47440)
2026-07-07 12:01:45 +00:00
nemotron_h.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
nemotron_nas.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
nemotron_parse.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
nemotron_vl.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
nemotron.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
nvlm_d.py
[Model] Remove Mono-InternVL (InternLM2VEForCausalLM) (#45129)
2026-06-12 10:41:09 +00:00
olmo3.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
olmo_hybrid.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
olmoe.py
[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)
2026-07-31 11:28:18 +01:00
openai_privacy_filter.py
[Model] Add support for openai/privacy-filter (#41026)
2026-06-28 16:18:22 -07:00
opencua.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
openpangu_mtp.py
…
openpangu_vl.py
[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)
2026-05-15 08:25:52 +08:00
openpangu.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
openvla.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
opt.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
orion.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
ovis2_5.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
ovis.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
paddleocr_vl.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
paligemma.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
parakeet.py
[Platform] Fill in the missing backend parameter for torch.compile (#51781)
2026-08-19 10:31:19 +00:00
param2moe.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
phi3.py
…
phi3v.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
phi4mm_audio.py
[Perf][4/n] Eliminate various GPU<->CPU syncs (#42347)
2026-05-19 10:35:54 -04:00
phi4mm_utils.py
[Refactor] Remove multiple dead codes (#50285)
2026-08-03 10:59:08 -04:00
phi4mm.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
phi4siglip.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
phi.py
Remove unnecessary load_weights methods (#44589)
2026-06-29 01:52:23 -07:00
phimoe.py
[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)
2026-07-31 11:28:18 +01:00
pixtral.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
plamo3.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
qianfan_ocr.py
[Model] support Qianfan-OCR model (#40136)
2026-05-05 10:51:25 +00:00
qwen2_5_omni_thinker.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
qwen2_5_vl.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
qwen2_audio.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
qwen2_moe.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
qwen2_rm.py
Remove unnecessary load_weights methods (#44589)
2026-06-29 01:52:23 -07:00
qwen2_vl.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
qwen2.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
qwen3_5_mtp.py
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
2026-08-18 12:56:56 -04:00
qwen3_5.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
qwen3_asr_forced_aligner.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
qwen3_asr_realtime.py
…
qwen3_asr.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
qwen3_dflash2.py
[Spec Decode] DFlash2: local convolution + candidate selector (#52816)
2026-08-20 22:27:22 -07:00
qwen3_dflash.py
[Spec Decode] DFlash2: local convolution + candidate selector (#52816)
2026-08-20 22:27:22 -07:00
qwen3_dspark.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
qwen3_eagle3.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
qwen3_moe.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
qwen3_next_mtp.py
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
2026-08-18 12:56:56 -04:00
qwen3_next.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
qwen3_omni_moe_thinker.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
qwen3_vl_moe.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
qwen3_vl.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
qwen3.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
radio.py
[Refactor] Remove dead code in multiple files (#49745)
2026-07-27 15:58:26 -04:00
registry.py
[Spec Decode] DFlash2: local convolution + candidate selector (#52816)
2026-08-20 22:27:22 -07:00
rnj1.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
roberta.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
rvl.py
…
sarvam.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
seed_oss.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
siglip2navit.py
Remove more unnecessary load_weights methods (#47058)
2026-06-30 15:22:16 +01:00
siglip.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
skyworkr1v.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
smolvlm.py
…
solar.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
stablelm.py
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
2026-08-13 15:10:09 +00:00
step1.py
Remove unnecessary load_weights methods (#44589)
2026-06-29 01:52:23 -07:00
step3_text.py
[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)
2026-07-31 11:28:18 +01:00
step3_vl.py
[MM] Keep more metadata tensors on CPU (#52827)
2026-08-18 19:56:33 -07:00
step3p5_mtp.py
fix(step3p5-mtp): honor exclude_modules for the MTP head via prefix (#48883)
2026-07-29 16:58:29 +00:00
step3p5.py
[Refactor] Delete dead code in models (#51838)
2026-08-11 15:44:26 -04:00
step3p7.py
[Model]Support Step-3.7-Flash (#43859)
2026-05-28 17:01:48 -07:00
step_vl.py
[MM][CG] Enable encoder Cudagraph for Step3VL (#42224)
2026-05-17 20:19:13 -07:00
telechat2.py
Fix weight tying (#51665)
2026-08-20 10:31:55 +00:00
teleflm.py
…
terratorch.py
[Core] Check for GPU<->CPU syncs during CI (#43107)
2026-08-14 17:42:05 -07:00
ultravox.py
[Bugfix][LoRA] Use an explicit capability flag for tower connector LoRA (#53092)
2026-08-21 09:45:54 +00:00
unlimited_ocr.py
Add Triton Backend for Unlimited-OCR R-SWA (#47102)
2026-07-03 00:11:50 -07:00
utils.py
Reduce AutoWeightsLoader kwargs (#53106)
2026-08-20 15:40:11 +00:00
vision.py
replace batch_norm to numerically identical without cudnn (#51734)
2026-08-11 12:43:20 +08:00
voxtral_realtime.py
[Bugfix][Voxtral Realtime] Fix token feedback timeout silent hang (#44461)
2026-07-05 05:42:36 -07:00
voxtral.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
voyage.py
[Model] Use AutoWeightsLoader for Voyage (#42972)
2026-05-22 05:28:23 +00:00
whisper_causal.py
[Bugfix] Fix pooled Whisper encoder sliding-window kernel size (#47437)
2026-07-02 10:19:11 -07:00
whisper_utils.py
…
whisper.py
[MM] Remove text components from ProcessorInputs (#53093)
2026-08-20 20:42:53 -07:00
zamba2.py
Remove more unnecessary load_weights methods (#47058)
2026-06-30 15:22:16 +01:00