Cancel PR Workflows on Merge

Actions

Cancel PR Workflows on Merge

Actions

Loading...
Loading

533 workflow runs

bugfix(hicache): Move exists check before key suffixing Cancel PR Workflows on Merge #533: Pull request #9749 closed by zhyncs

August 29, 2025 01:29

[HiCache] change the default policy to write through Cancel PR Workflows on Merge #532: Pull request #9772 closed by zhyncs

August 29, 2025 01:28

Optimize prefill performance on cpu backend Cancel PR Workflows on Merge #531: Pull request #8750 closed by zhyncs

August 29, 2025 00:21

fix: fix MLA for ShardedModelLoader/RemoteModelLoader Cancel PR Workflows on Merge #530: Pull request #6287 closed by zhyncs

August 28, 2025 23:10

feat(draft_model): support draft_model for RemoteModelLoader Cancel PR Workflows on Merge #529: Pull request #6407 closed by zhyncs

August 28, 2025 23:09

[Feature] Support NPUGraph for DeepSeek on Ascend NPU Cancel PR Workflows on Merge #528: Pull request #9355 closed by zhyncs

August 28, 2025 23:06

feat: add tuned fused moe config for GLM-4.5-Air-FP8 tp = 4 on B200 Cancel PR Workflows on Merge #527: Pull request #9770 closed by zhyncs

August 28, 2025 23:00

10s

August 28, 2025 23:00

10s

[AMD] Support Hierarchical Caching on AMD GPUs Cancel PR Workflows on Merge #526: Pull request #8236 closed by zhyncs

August 28, 2025 22:27

[router] grpc router bootstraps Cancel PR Workflows on Merge #525: Pull request #9759 closed by slin1237

August 28, 2025 19:07

[Sync] Update server_args.py (20250828) Cancel PR Workflows on Merge #524: Pull request #9745 closed by merrymercy

August 28, 2025 17:33

Support compile sgl-kernel on cuda 13.0 Cancel PR Workflows on Merge #523: Pull request #9721 closed by rainj-me

August 28, 2025 17:18

[router] add llama3.2 multi json streaming parser Cancel PR Workflows on Merge #522: Pull request #9735 closed by slin1237

August 28, 2025 12:57

11s

August 28, 2025 12:57

11s

Support speculative decoding in hybrid attention backend Cancel PR Workflows on Merge #521: Pull request #9573 closed by zhyncs

August 28, 2025 08:11

10s

August 28, 2025 08:11

10s

[feat] Reduce GPU memory overhead by using weakref Cancel PR Workflows on Merge #520: Pull request #9673 closed by zhyncs

August 28, 2025 08:09

Move git clone command up from README Cancel PR Workflows on Merge #519: Pull request #9740 closed by zhyncs

August 28, 2025 07:27

11s

August 28, 2025 07:27

11s

add support for nvidia/gpt-oss-120b-Eagle3 Cancel PR Workflows on Merge #518: Pull request #9739 closed by zhyncs

August 28, 2025 07:20

support mooncake store dp attention Cancel PR Workflows on Merge #517: Pull request #9684 closed by hnyls2002

August 28, 2025 04:31

Router ut 1 Cancel PR Workflows on Merge #516: Pull request #9734 closed by slin1237

August 28, 2025 04:17

[router] additional llama32 parser unit test and multi json support Cancel PR Workflows on Merge #515: Pull request #9732 closed by slin1237

August 28, 2025 03:34

[router] additional pythonic parser unit test Cancel PR Workflows on Merge #514: Pull request #9730 closed by slin1237

August 28, 2025 02:56

gpt-oss blog reproduction document Cancel PR Workflows on Merge #513: Pull request #9728 closed by hnyls2002

August 28, 2025 02:15

[router] Add MCP Tool Handler Cancel PR Workflows on Merge #512: Pull request #9615 closed by slin1237

August 28, 2025 02:12

12s

August 28, 2025 02:12

12s

[router] fix error response in pd_router Cancel PR Workflows on Merge #511: Pull request #9505 closed by slin1237

August 28, 2025 02:10

[Sync] Update mxfp4.py (20250827) Cancel PR Workflows on Merge #510: Pull request #9724 closed by merrymercy

August 28, 2025 00:00

[Sync] Update mxfp4.py (20250827) Cancel PR Workflows on Merge #509: Pull request #9714 closed by merrymercy

August 27, 2025 23:45

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Actions

Workflows

Management