Skip to content

QSA decode attention: PR #540's two-cells-per-step chunk kernel on every CUDA card and a bounded merge (STRATA_ATTN_DAILY=1, opt-in, bit-exact) - #2075

Closed
imanu86 wants to merge 1 commit into
Niko1221:mainfrom
imanu86:pr/attn-daily
Closed

QSA decode attention: PR #540's two-cells-per-step chunk kernel on every CUDA card and a bounded merge (STRATA_ATTN_DAILY=1, opt-in, bit-exact)#2075
imanu86 wants to merge 1 commit into
Niko1221:mainfrom
imanu86:pr/attn-daily

QSA decode attention: PR #540's two-cells-per-step chunk kernel on ev…

901de01
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs