Didan Deng 43ec7f701b [Feature] Flash Attention to Support Attention Mask (#760) ...

Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>

2026-01-16 11:01:11 +08:00

..

diffusion

[Feature] Flash Attention to Support Attention Mask (#760)

2026-01-16 11:01:11 +08:00

distributed/omni_connectors

[Security][Feature] Use Msgpack in OmniSerializer instead of pickle (#310)

2025-12-22 13:21:16 +13:00

e2e

[feature] cpu offloading support for diffusion (#497)

2026-01-12 10:41:18 +00:00

entrypoints

omni entrypoint support tokenizer arg (#572)

2026-01-08 15:44:14 +08:00

model_executor/models/qwen2_5_omni

[Bugfix]Fix Qwen 2.5 omni hardcoded max_mel_frames to resolve shape mismatch (#543)

2026-01-01 17:12:03 +13:00

worker

[Feature] Support Qwen3 Omni talker mtp batch inference (#722)

2026-01-14 19:07:31 +08:00

__init__.py

[Fix] Resolve comments & update vLLM-Omni name usages. (#122)

2025-12-01 08:05:24 +08:00

conftest.py

[Core] add clean up method for diffusion engine (#219)

2025-12-08 03:52:07 +00:00

utils.py

[CI] Add pytest markers in config files. (#719)

2026-01-14 20:35:26 +08:00