leo e24bddfb22 Fix Qwen3-Omni thinker fused MoE LoRA (#5191) ...

Signed-off-by: leo <yaoliu548926@gmail.com>

2026-07-20 08:52:21 -07:00

..

__init__.py

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760)

2026-06-24 11:02:29 +08:00

pipeline.py

[Config] Return VllmOmniConfig from create_from_model (#4818)

2026-07-18 09:21:07 +00:00

qwen3_omni_code2wav.py

[BugFix] Fix Code2Wav async_chunk streaming tail drop (boundary clicks + ~1.2% time compression) (#4706)

2026-07-02 09:13:42 +08:00

qwen3_omni_moe_code_predictor_mtp.py

[NPU] Support code predictor NPU graph (#2695)

2026-04-22 10:15:08 +00:00

qwen3_omni_moe_talker.py

[Feat] Support Pipeline Resolution Based on HF Config & Make Pipeline Registry Eager (#3760)

2026-06-24 11:02:29 +08:00

qwen3_omni_moe_thinker.py

Fix Qwen3-Omni thinker fused MoE LoRA (#5191)

2026-07-20 08:52:21 -07:00

qwen3_omni.py

[Refactor] Replace hardcoded CUDA device selection with platform-agnostic API (#4496)

2026-06-23 14:38:32 +08:00