Skip to content

perf(glm): write MLA projections directly in token-major layout - #1710

Merged
shihaobai merged 2 commits into
mainfrom
bsh/glm-prefill-mla-token-major-bmm
Nov 12, 2026
Merged

perf(glm): write MLA projections directly in token-major layout#1710
shihaobai merged 2 commits into
mainfrom
bsh/glm-prefill-mla-token-major-bmm

perf(glm): simplify token-major projections and cover decode

fc84574
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar