Chenguang Zhengandamy-why-3459 eaa16e1941 [Feature] Support Async Omni output materialization (#4476) ...

Signed-off-by: Chenguang ZHENG <645327136@qq.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>

2026-06-22 16:07:07 +00:00

..

__init__.py

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

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

pipeline.py

[2/5] [core]refactor communication layer: PR 2 of 5 Qwen3 Omni non async (#2677)

2026-05-15 14:14:08 +08:00

qwen3_omni_code2wav.py

[BugFix] code2wav supports disabling CUDA graph. (#3732)

2026-05-24 00:05:55 +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

[Perf] Remove dead audio_tower and visual from Qwen3-Omni talker stage (#3296)

2026-05-11 16:04:56 +00:00

qwen3_omni_moe_thinker.py

[Bugfix][Qwen3-Omni] Pass Thinker lm_head prefix so NVFP4 exclude-list is honored (#4528)

2026-06-22 12:16:44 +08:00

qwen3_omni.py

[Feature] Support Async Omni output materialization (#4476)

2026-06-22 16:07:07 +00:00