TrainToGPBandClaude eb3dce9757 [Bugfix][Model] Gemma3n/Gemma4: pad variable-length audio batches (#50958) ...

Signed-off-by: TrainToGPB <kaiba0514@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

2026-08-05 12:46:00 +08:00

..

generation

[Bugfix][Model] Gemma3n/Gemma4: pad variable-length audio batches (#50958)

2026-08-05 12:46:00 +08:00

generation_ppl_test

[CI] And PPL test for multimodal generation models (#50839)

2026-08-03 11:25:08 +00:00

pooling

[Bugfix] Respect declared attention contract for ColQwen3.5 retrievers (#49372)

2026-07-26 04:08:07 +00:00

processing

[Bugfix] Fix Qwen3-Omni crash on video with no audio track when use_audio_in_video=True (#48420)

2026-08-03 16:22:00 -07:00

__init__.py

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

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

conftest.py

Deprecated 1st generation Qwen and QwenVL models (#45131)

2026-06-10 14:55:33 +00:00

test_mapping.py

[bugfix] Fix Cosmos3 Edge checkpoint weights filtering, video loading, prompt expansion (#49190)

2026-07-21 17:18:36 +08:00

test_nano_nemotron_vl.py

Avoid silent weights corruption when loading Nemotron Nano VL with reusable-buffer loaders like runai distributed streaming (#42244)

2026-05-11 12:03:14 +00:00