tzhouam 08fa85a1ad Update audio tensor access in offline inference tests and increase image fetch timeout for CI ...

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

2026-02-02 06:10:54 +00:00

..

benchmarks

[Bugfix] fix benchmark audio timing error and add benchmark test (#1109)

2026-01-31 10:15:26 +08:00

diffusion

[Perf]: CFG parallel abstraction (#851)

2026-01-30 16:23:44 +00:00

distributed/omni_connectors

[Core]: KV Cache Transfer Encapsulation (#979)

2026-01-28 23:12:45 +08:00

e2e

Update audio tensor access in offline inference tests and increase image fetch timeout for CI

2026-02-02 06:10:54 +00:00

entrypoints

[FEATURE] /v1/images/edit interface (#1101)

2026-01-31 14:13:36 +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

[BugFix] Fix Qwen3 Omni talker mtp torch.compile startup error (#1104)

2026-01-30 23:25:49 +08:00

__init__.py

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

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

conftest.py

[Fix] Increase max wait time for server readiness to accommodate model loading (#1089)

2026-01-30 11:27:19 +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

[Test]Delete skip mark for amd ci test and fix CI failure (#927)

2026-01-29 16:21:24 +13:00