dsinghvi 59024bee62 Process-Scoped GPU Memory Accounting (#1204) ...

Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>

2026-02-08 22:43:02 +08:00

..

benchmarks

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

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

diffusion

[Bugfix] Fix tp+sp accuracy, incorrect process group mapping (#1178)

2026-02-04 16:54:47 +08:00

distributed/omni_connectors

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

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

e2e

[Test] Add BuildKite test-full script for full CI. (#867)

2026-02-06 01:19:46 +08:00

entrypoints

[Bugfix] Ensure seed=0 is correctly handled in image edit (#1248)

2026-02-07 07:09:54 +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

Process-Scoped GPU Memory Accounting (#1204)

2026-02-08 22:43:02 +08:00

__init__.py

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

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

conftest.py

[CI] Add CI branch coverage calculation, fix statement coverage results and add log before test for buildkite log group (#1120)

2026-02-05 10:54:40 +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