llama.cpp
CUDA: Small optimizations to MMVQ
#25445
Merged

CUDA: Small optimizations to MMVQ #25445

ORippler
ORippler Only index by compile times + always multiply/add
d1fdb6b7
ORippler ORippler requested a review 121 days ago
github-actions github-actions added ggml
github-actions github-actions added CUDA
am17an
am17an approved these changes on 2026-07-09
gaugarg-nv
gaugarg-nv approved these changes on 2026-07-09
ORippler ORippler merged 683f0c72 into master 120 days ago
ORippler ORippler deleted the osimons/mmvq_optimizations branch 120 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone