Skip to content

CUDA: Improve performance via less synchronizations between token#17795

Merged
ggerganov merged 13 commits into
ggml-org:masterfrom
aendk:akieslinger/reduce-per-token-syncs
Mar 5, 2026
Merged

CUDA: Improve performance via less synchronizations between token#17795
ggerganov merged 13 commits into
ggml-org:masterfrom
aendk:akieslinger/reduce-per-token-syncs

Apply suggestion from @ggerganov (src->buffer to buf_src) v2

81c9618
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

The logs for this run have expired and are no longer available.