5 people c3ad791e1a [Bugfix][Gemma 4] Clamp soft-token estimate to max_soft_tokens (#40796) ...

Signed-off-by: Hoang Nguyen <118159510+hnt2601@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2026-05-02 06:34:59 +00:00

..

__init__.py

[CI/Build] Move model-specific multi-modal processing tests (#11934)

2025-01-11 13:50:05 +08:00

test_audio_in_video.py

[Bugfix] Fix Qwen2.5-Omni/Qwen3-Omni use_audio_in_video with multi-video inputs (#37147)

2026-03-16 08:56:06 +00:00

test_audioflamingo3.py

[Bugfix] Fix audioflamingo test (#40052)

2026-04-16 11:53:58 -07:00

test_common.py

Fix Cohere ASR after HF upgrade (#40582)

2026-04-29 23:39:04 -07:00

test_deepseek_ocr.py

[Bugfix][Model] Fix DeepSeek-OCR TensorSchema crash on empty images_crop (#36670)

2026-03-12 15:35:54 +08:00

test_gemma3.py

[Misc] Standardize handling of mm_processor_kwargs.size (#35284)

2026-02-26 13:05:46 +00:00

test_gemma4.py

[Bugfix][Gemma 4] Clamp soft-token estimate to max_soft_tokens (#40796)

2026-05-02 06:34:59 +00:00

test_glm4_1v.py

[Multimodal] Add PyAV video backend for concurrent video decoding (#39986)

2026-04-21 20:14:57 -07:00

test_h2ovl.py

[1/2] Move InternVL-based processors (#37260)

2026-03-17 21:50:56 +08:00

test_idefics3.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_internvl.py

[1/2] Move InternVL-based processors (#37260)

2026-03-17 21:50:56 +08:00

test_llama4.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_llava_next.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_llava_onevision.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_minimax_vl_01.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_mllama4.py

[Misc] Make PlaceholderRange.get_num_embeds a method (#34035)

2026-02-07 05:30:17 +00:00

test_moondream3.py

[Model] Add Moondream3 model support(only query and caption skills) (#32325)

2026-05-01 10:06:48 +08:00

test_musicflamingo.py

Update to transformers v5 (#30566)

2026-04-15 16:29:15 -07:00

test_nemotron_vl.py

[1/2] Move InternVL-based processors (#37260)

2026-03-17 21:50:56 +08:00

test_phi3v.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_phi4mm.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_qwen2_5_omni_embed.py

[Model] Remove unused handle_oov_mm_token (#37321)

2026-03-17 19:44:52 +00:00

test_qwen2_vl.py

[Misc] Standardize handling of mm_processor_kwargs.size (#35284)

2026-02-26 13:05:46 +00:00

test_qwen3_omni.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_qwen3_vl.py

[Bugfix] Fix Qwen3-VL timestamp mismatch when using num_frames without fps (#36136)

2026-03-11 03:13:06 -07:00

test_smolvlm.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00

test_tensor_schema.py

Reapply [Attention] Refactor check_and_update_config (#35122)

2026-03-09 07:17:14 -07:00

test_transformers.py

[Refactor] Decouple TimingContext from InputProcessingContext (#35083)

2026-02-23 14:15:50 +00:00