llama.cpp
CUDA: more warps for mmvq on NVIDIA
#5394
Merged
Overview
Commits
1
Changes
View On GitHub

CUDA: more warps for mmvq on NVIDIA #5394

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-faster-mmvq-9
JohannesGaessler
sorasoras
JohannesGaessler
sorasoras
8XXD8
JohannesGaessler
8XXD8
slaren
slaren commented on 2024-02-08
JohannesGaessler CUDA: more warps for mmvq on NVIDIA
00ebc310
JohannesGaessler JohannesGaessler force pushed to 00ebc310 2 years ago
slaren
slaren
slaren approved these changes on 2024-02-08
JohannesGaessler
JohannesGaessler JohannesGaessler merged 8e6a9d2d into master 2 years ago
Ph0rk0z
JohannesGaessler
Ph0rk0z
JohannesGaessler
Ph0rk0z
JohannesGaessler

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum