3 people 9f9e1dac26 [Bugfix][Model] Restore causal image SWA for DeepSeek V4.1 (#57152) ...

Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>

2026-09-16 18:09:00 +00:00

..

speculators

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

__init__.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

afmoe.py

Update rope_scaling to rope_parameters in preparation for Transformers v5 (#28542)

2025-11-19 09:06:36 -08:00

AXK1.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

bagel.py

[New Model] BAGEL support (AR only) (#28439)

2025-12-15 14:58:23 +08:00

bailing_moe_v3_vl.py

[Model] Add Bailing V3 VL support (#55921)

2026-09-10 02:46:56 -07:00

chatglm.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

colmodernvbert.py

[Model] Update ColModernVBERT to support latest HF checkpoint (#39307)

2026-04-09 10:48:51 +08:00

colpali.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

colqwen3.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

cosmos3_edge.py

Add Cosmos3 Edge Reasoner model (#48291)

2026-07-14 08:14:50 +00:00

cosmos3.py

Add Cosmos3 Reasoner model (#43356)

2026-05-28 09:43:55 -07:00

deepseek_v4.py

[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)

2026-09-02 11:09:09 -07:00

deepseek_v41.py

[Bugfix][Model] Restore causal image SWA for DeepSeek V4.1 (#57152)

2026-09-16 18:09:00 +00:00

deepseek_vl2.py

[Bugfix][Model] deepseek-vl2: restore original DeepseekV2Config defaults for omitted language_config fields (#51302)

2026-08-25 05:03:40 +00:00

diffusion_gemma.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

dots3_note.py

[Model] Add native Dots3 NOTE multimodal support (#51255)

2026-08-12 23:13:20 +08:00

dotsocr.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

eagle.py

[Feat][Spec Decode] DFlash (#36847)

2026-03-30 15:03:15 -04:00

extract_hidden_states.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

falcon.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

funaudiochat.py

[CI] Bump mypy version to 1.19.1 (#36104)

2026-03-10 09:18:28 -07:00

gemma4.py

Fix Gemma 4 for upcoming Transformers version (#49797)

2026-08-10 07:48:26 +00:00

glm5_next.py

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

granite4_vision.py

Add Granite 4.1 Vision as built-in multimodal model (#40282)

2026-04-21 05:43:39 -07:00

hy_v3.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

hy_v4.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

hyperclovax.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

isaac.py

Various Transformers v5 config fixes (#38247)

2026-03-26 23:06:59 +00:00

k3_dspark.py

[Bugfix][Model] Fix K3 DSpark config for 96-head drafts (#54005)

2026-08-27 15:58:28 -07:00

kimi_k3.py

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

2026-07-29 14:10:58 +08:00

kimi_k25.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

kimi_linear.py

[New model] Kimi K3 (#50000)

2026-07-30 03:49:58 -07:00

kimi_vl.py

[Chore] Clean up deepseek v2/v3 config copy (#28055)

2025-11-06 03:46:30 +00:00

lfm2_moe.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

medusa.py

[BugFix] Avoid ignored trust_remote_code warnings (#36290)

2026-03-07 01:24:18 +00:00

midashenglm.py

Update rope_scaling to rope_parameters in preparation for Transformers v5 (#28542)

2025-11-19 09:06:36 -08:00

mimo_v2_omni.py

[Model] Add MiMo-V2.5 support (#40967)

2026-04-27 13:26:51 +00:00

minimax_m3.py

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

mistral.py

[Bugfix] Align vLLM YaRN with Transformers and stop re-scaling max_model_len (#56446)

2026-09-11 13:01:38 +00:00

mlp_speculator.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

moondream3.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

moonvit.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

moss_transcribe_diarize.py

[Model] Support MOSS-Transcribe-Diarize (#47729)

2026-07-08 04:05:45 -07:00

muse_glimmer.py

Add Muse Glimmer model support (#51655)

2026-08-14 12:28:56 +08:00

nemotron_h.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

nemotron.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

olmo_hybrid.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

openvla.py

[Model] Openvla support (#42654)

2026-05-19 08:17:42 -07:00

ovis.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

parakeet.py

ParakeetExtractor performance and UX enhancements (#39423)

2026-04-13 21:37:35 +00:00

qianfan_ocr.py

[Model] support Qianfan-OCR model (#40136)

2026-05-05 10:51:25 +00:00

qwen3_5_moe.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

qwen3_5.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

qwen3_asr.py

[Rust Frontend] Integrate MM audio support (#48554)

2026-07-15 15:00:17 +08:00

qwen3_next.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

qwen4_exp.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

radio.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

step3_vl.py

Update rope_scaling to rope_parameters in preparation for Transformers v5 (#28542)

2025-11-19 09:06:36 -08:00

step3p5.py

Various Transformers v5 config fixes (#38247)

2026-03-26 23:06:59 +00:00

ultravox.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

unlimited_ocr.py

[Model] Support Unlimited OCR (#46564)

2026-06-27 23:09:18 -07:00