Zeyu Huang | 黃澤宇 d64bbde561 [Frontend][Model] Support batch request with refined OmniDiffusionReq… (#797) ...

Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>

2026-01-28 16:07:42 +08:00

..

diffusion

[test] revert test flash attn file (#972)

2026-01-27 08:39:07 +00:00

distributed/omni_connectors

[Frontend][Model] Support batch request with refined OmniDiffusionReq… (#797)

2026-01-28 16:07:42 +08:00

e2e

[Frontend][Model] Support batch request with refined OmniDiffusionReq… (#797)

2026-01-28 16:07:42 +08:00

entrypoints

[Frontend][Model] Support batch request with refined OmniDiffusionReq… (#797)

2026-01-28 16:07:42 +08:00

model_executor/models/qwen2_5_omni

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

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

worker

[Model] Support Qwen3-TTS model series (#895)

2026-01-22 16:57:37 +08:00

__init__.py

[Fix] Resolve comments & update vLLM-Omni name usages. (#122)

2025-12-01 08:05:24 +08:00

conftest.py

[Test] Add chunk e2e test case for CI (#956)

2026-01-27 20:15:56 +08:00

test_outputs.py

[BugFix] Add /health and /v1/models endpoints for diffusion mode, fix streaming compatibility (#454)

2026-01-28 13:11:15 +08:00

utils.py

[CI] split tests to avoid timeout (#883)

2026-01-21 15:12:45 +08:00