llama : reuse the tensor staging buffer and skip the direct-io bounce buffer #31321
llama : reuse the tensor staging buffer and skip the direct-io bounceā¦
a3185dea
am17an
requested a review
25 days ago
ggerganov
approved these changes
on 2026-10-29
am17an
merged
0ac1a7fd
into master 24 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub