llama.cpp
metal: Reducing base memory use
#5161
Merged

metal: Reducing base memory use #5161

ggerganov merged 6 commits into ggml-org:master from metal-memory-reduction
ptsochantaris
ptsochantaris Releasing MTLFunction references after Metal pipeline construction
266349ae
ptsochantaris Merge branch 'master' into metal-memory-use-reduction
e258f294
ggerganov
ggerganov approved these changes on 2024-01-28
ggerganov
ggerganov
ptsochantaris
ptsochantaris Keeping the `ggml_metal_kernel` structure
1b592aa8
ptsochantaris Merge branch 'master' into metal-memory-reduction
c846c451
ptsochantaris Spacing fix
855645a0
ptsochantaris
ptsochantaris
ggerganov
ggerganov approved these changes on 2024-01-28
ptsochantaris Whitespace fix
4eafb833
ggerganov ggerganov merged d2f650cb into master 1 year ago
ptsochantaris ptsochantaris deleted the metal-memory-reduction branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone