范裕达 185cada36b [Model] Fix KV cache layout and optimize Dots3 NOTE Omni encoders (#53460) ...

Signed-off-by: KurodaKanbei <mistergalahad@gmail.com>

2026-08-23 10:02:35 -07:00

..

__init__.py

…

attention.py

[Model] Fix KV cache layout and optimize Dots3 NOTE Omni encoders (#53460)

2026-08-23 10:02:35 -07:00

audio_encoder.py

[Docs] Fix WhisperEncoderLayer.forward docstring in dots3_note (#52134)

2026-08-13 02:32:14 -07:00

audio.py

[Model] Fix KV cache layout and optimize Dots3 NOTE Omni encoders (#53460)

2026-08-23 10:02:35 -07:00

model.py

[Bugfix] Disable sequence parallelism for Dots3 NOTE (#52172)

2026-08-13 22:13:00 +08:00

mtp.py

…

multimodal.py

[Model] Fix KV cache layout and optimize Dots3 NOTE Omni encoders (#53460)

2026-08-23 10:02:35 -07:00

vision_attention.py

[Model] Fix KV cache layout and optimize Dots3 NOTE Omni encoders (#53460)

2026-08-23 10:02:35 -07:00

vision_moe.py

…

vision.py

[Model] Fix KV cache layout and optimize Dots3 NOTE Omni encoders (#53460)

2026-08-23 10:02:35 -07:00