Skip to content

[Kernel] Separate Triton Attention Kernel Launches for Prefill and Decode for FULL CUDA Graph mode#29020

Open
jvlunteren wants to merge 19 commits intovllm-project:mainfrom
jvlunteren:jvl-triton-attn-upd5
Open

[Kernel] Separate Triton Attention Kernel Launches for Prefill and Decode for FULL CUDA Graph mode#29020
jvlunteren wants to merge 19 commits intovllm-project:mainfrom
jvlunteren:jvl-triton-attn-upd5

Commits

Commits on Nov 19, 2025

Commits on Nov 20, 2025

Commits on Nov 21, 2025

Commits on Nov 29, 2025

Commits on Dec 1, 2025

Commits on Dec 2, 2025

Commits on Dec 3, 2025

Commits on Dec 4, 2025