tzhouam 3e89c99001 Merge remote-tracking branch 'remotes/origin/main' into dev/vllm-align

2026-02-12 07:16:25 +00:00

..

__init__.py

[Feature] add support for Qwen3-omni (#55)

2025-11-30 04:44:01 +08:00

qwen3_moe.py

[Feature] add support for Qwen3-omni (#55)

2025-11-30 04:44:01 +08:00

qwen3_omni_code2wav.py

[Pref] Support Qwen3 Omni code2wav batch infernce with async chunk (#1246)

2026-02-12 11:50:10 +08:00

qwen3_omni_moe_code_predictor_mtp.py

[BugFix] Fix Qwen3 Omni talker mtp torch.compile startup error (#1104)

2026-01-30 23:25:49 +08:00

qwen3_omni_moe_talker.py

[Refactor] Reuse upstream Qwen3MoeSparseMoeBlock (#1202)

2026-02-06 01:06:50 +00:00

qwen3_omni_moe_thinker.py

Refactor OmniEngineArgs and AsyncOmniEngineArgs to improve compatibility with partial payloads by using getattr for various attributes. Update GPUGenerationModelRunner and OmniGPUModelRunner to replace the activate_lora parameter with num_active_loras for better clarity and backward compatibility. This change enhances the handling of LoRA activation during model runs.

2026-02-12 03:33:50 +00:00

qwen3_omni.py

[Pref] Support Qwen3 Omni code2wav batch infernce with async chunk (#1246)

2026-02-12 11:50:10 +08:00