Skip to content

perf(glm): reuse Triton kernels across query and pool lengths - #1684

Open
shihaobai wants to merge 1 commit into
mainfrom
codex/glm-length-kernel-cache
Open

perf(glm): reuse Triton kernels across query and pool lengths#1684
shihaobai wants to merge 1 commit into
mainfrom
codex/glm-length-kernel-cache

perf(glm): reuse length-dependent kernel binaries

4803608
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar