llama.cpp
llama : reuse the tensor staging buffer and skip the direct-io bounce buffer
#31321
Merged

llama : reuse the tensor staging buffer and skip the direct-io bounce buffer #31321

am17an merged 1 commit into master from aman/loader-staging-reuse
am17an
am17an llama : reuse the tensor staging buffer and skip the direct-io bounce…
a3185dea
am17an am17an requested a review 25 days ago
ServeurpersoCom
ServeurpersoCom approved these changes on 2026-10-28
ggerganov
ggerganov approved these changes on 2026-10-29
am17an am17an merged 0ac1a7fd into master 24 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone