amy-why-3459 335e2eb9e4 [perf]Qwen3-Omni performance optimization (#3164) ...

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>

2026-04-28 11:59:26 +08:00

..

cli

Benchmark and Bugfix for GLM-Image (#3024)

2026-04-25 20:49:19 +08:00

openai

[perf]Qwen3-Omni performance optimization (#3164)

2026-04-28 11:59:26 +08:00

__init__.py

[Bug] Lazy-import entrypoints to fix subprocess pynvml crash (#2187)

2026-04-09 15:35:22 +08:00

async_omni.py

[Refactor/Bugfix] Use Delta Messages for Streaming (#2911)

2026-04-26 15:11:53 +12:00

chat_utils.py

[Refactor] Remove dependency on librosa (#2273)

2026-04-11 02:11:31 +08:00

client_request_state.py

[Feature] Opt metrics structure (#891)

2026-02-09 19:17:32 +08:00

omni_base.py

[Refactor/Bugfix] Use Delta Messages for Streaming (#2911)

2026-04-26 15:11:53 +12:00

omni.py

[Enhancement] Engine runtime errors (#2426)

2026-04-21 14:46:05 +08:00

pd_utils.py

[Feature] Support Prefill-Decode disaggregation via vLLM KV transfer (#2220)

2026-04-17 18:43:17 +08:00

stage_utils.py

[Bugfix] Fix precedence between caller runtime args and default stage configs (#2076)

2026-04-09 16:44:31 +08:00

utils.py

[Refactor/Bugfix] Use Delta Messages for Streaming (#2911)

2026-04-26 15:11:53 +12:00