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] support multimodal inputs with multiple requests (#76)

2025-11-24 16:02:44 +08:00

audio_length.py

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

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

qwen2_5_omni_talker.py

[Perf] Optimize the Qwen2.5-Omni Model thinker-to-talker-proj with nn.Linear (#825)

2026-01-17 19:47:11 +08:00

qwen2_5_omni_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

qwen2_5_omni_token2wav.py

[Feat] Support XPU Backend in vLLM-Omni (#191)

2026-01-30 04:33:05 +13:00

qwen2_5_omni.py

update qwen 2.5 Omni

2026-02-02 03:01:11 +00:00

qwen2_old.py

debug

2026-02-12 14:20:57 +00:00