Skip to content

cuda: fuse MoE expert weighting and reduction (+3% to +9% prefill, MoE models only) - #26160

Closed
coder543 wants to merge 1 commit into
ggml-org:masterfrom
coder543:perf/moe-weighted-reduction
Closed

cuda: fuse MoE expert weighting and reduction (+3% to +9% prefill, MoE models only)#26160
coder543 wants to merge 1 commit into
ggml-org:masterfrom
coder543:perf/moe-weighted-reduction

cuda: fuse MoE expert weighting and reduction

acf9c9e
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
labeler
succeeded Jul 27, 2026 in 19s