llama-bench: print `-n-cpu-moe` when offloaded layers > 1 #20984
am17an
merged
1 commit into
ggml-org:master
from
am17an:n-cpu-moe-llama-bench
llama-bench: print `-n-cpu-moe` when offloaded layers > 1
12dc4de2
CISC
approved these changes
on 2026-03-25
JohannesGaessler
approved these changes
on 2026-03-25
ggerganov
approved these changes
on 2026-03-25
Reviewers
Assignees
No one assigned
Labels
examples
Milestone
No milestone
Login to write a write a comment.
Login via GitHub