Skip to content

CUDA: branchless Q4_K/Q5_K unpack to speed up mmvq, L2 prefetch on DGX Spark - #26705

Merged
am17an merged 10 commits into
ggml-org:masterfrom
praneshgo:pgonegandla/mmvq-q4k-q5k-branchless
Sep 7, 2026
Merged

CUDA: branchless Q4_K/Q5_K unpack to speed up mmvq, L2 prefetch on DGX Spark#26705
am17an merged 10 commits into
ggml-org:masterfrom
praneshgo:pgonegandla/mmvq-q4k-q5k-branchless

Fix build error on non-Spark CUDA arch with appropriate conditional a…

aa17a1b
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
labeler
succeeded Sep 7, 2026 in 14s