llama.cpp
ggml-cuda: tune RDNA3 Q4_K MMVQ nwarps
#23528
Merged

ggml-cuda: tune RDNA3 Q4_K MMVQ nwarps #23528

IMbackK merged 1 commit into ggml-org:master from ravel7524:master
ravel7524
ravel7524 ravel7524 requested a review 177 days ago
JohannesGaessler
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
ravel7524
JohannesGaessler
JohannesGaessler approved these changes on 2026-05-24
JohannesGaessler JohannesGaessler requested a review from IMbackK IMbackK 175 days ago
ravel7524 ravel7524 closed this 174 days ago
ravel7524 ravel7524 force pushed to 35c9b1f3 174 days ago
ravel7524 Remove case for GGML_TYPE_Q4_K in mvvq.cu
3235914c
ravel7524 ravel7524 reopened this 174 days ago
IMbackK IMbackK assigned IMbackK IMbackK 171 days ago
ravel7524
IMbackK
IMbackK approved these changes on 2026-06-08
ravel7524
IMbackK IMbackK merged e3471b3e into master 159 days ago

Login to write a write a comment.

Login via GitHub

Assignees
Labels
Milestone