llama.cpp
ggml-backend : prefetch only inputs computed by earlier splits
#32100

Merged

ggml-backend : prefetch only inputs computed by earlier splits #32100

am17an merged 2 commits into master from aman/sched-prefetch-compute-only

ggml-backend : prefetch only inputs computed by earlier splits

316d5877

llama : skip the MoE cache when its device cannot run the cached mul_…

4faf40c0

github-actions added ggml

am17an marked this pull request as ready for review 2 days ago

am17an requested a review from

CISC 2 days ago

CISC approved these changes on 2026-11-11

ggerganov approved these changes on 2026-11-11

am17an merged 3bce8bd5 into master 1 day ago

Reviewers

ggerganov

CISC

Assignees

No one assigned

Labels

ggml

Milestone

No milestone