tzhouam 8a4eee9bed Enhance configuration and debugging: Added asyncio mode to pytest settings, increased timeout for Qwen3-TTS E2E test, and improved logging in GPU model runner for better traceability of input modalities. Updated Dockerfile.ci to streamline VLLM installation process. ...

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

2026-02-13 06:39:28 +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

Enhance configuration and debugging: Added asyncio mode to pytest settings, increased timeout for Qwen3-TTS E2E test, and improved logging in GPU model runner for better traceability of input modalities. Updated Dockerfile.ci to streamline VLLM installation process.

2026-02-13 06:39:28 +00:00

qwen3_omni.py

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

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