llama.cpp
llama : reduce useless copies when saving session
#8916
Merged

llama : reduce useless copies when saving session #8916

compilade merged 2 commits into master from compilade/faster-session-sizes
compilade
compilade llama : avoid useless copies in dummy session writer
dca7ad86
compilade llama : avoid double tensor copy when saving session to buffer
9329953a
compilade compilade added performance
compilade compilade added bugfix
compilade compilade added Review Complexity : Low
slaren
slaren approved these changes on 2024-08-07
josharian
ggerganov
ggerganov approved these changes on 2024-08-08
josharian
compilade compilade merged 345a686d into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone