3 people 596c16a550 [Kernel] Fuse Q/K RMSNorm and RoPE (#5990) ...

Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Signed-off-by: Mengjie Zhao <zmj0129@gmail.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>

2026-08-14 00:46:59 +00:00

..

accuracy

[Kernel] Fuse Q/K RMSNorm and RoPE (#5990)

2026-08-14 00:46:59 +00:00

features

[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

2026-08-12 22:58:23 +08:00

offline_inference

[Refactor] Remove internal stage_configs_path plumbing (#5741)

2026-08-13 21:29:03 +08:00

online_serving

[Feat] LTX Standard Two-Stage Pipeline (#5500)

2026-08-14 00:13:14 +08:00

__init__.py

[ROCm] [CI] Add ROCm Dockerfile and AMD CI (vllm v0.12.0) (#280)

2025-12-21 11:51:37 +08:00