Junhong Liu d0836d8459 [Bugfix] Fix multi-audio input shape alignment for Qwen3-Omni Thinker (#697) ...

Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>

2026-01-12 13:16:29 +08:00

..

__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

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

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

qwen3_omni_moe_code_predictor_mtp.py

[Perf][Qwen3-Omni] Fuse QKV linear and gate_up proj (#734)

2026-01-11 11:06:24 +08:00

qwen3_omni_moe_talker.py

[Perf] Use vLLM's SharedFusedMoE in Qwen3-Omni (#560)

2026-01-10 04:30:06 +00:00

qwen3_omni_moe_thinker.py

[Bugfix] Fix multi-audio input shape alignment for Qwen3-Omni Thinker (#697)

2026-01-12 13:16:29 +08:00

qwen3_omni.py

[Feature] Support Qwen3 Omni talker cudagraph (#669)

2026-01-09 11:45:58 +08:00