llama.cpp
CUDA: use min compute capability of GPUs actually used
#2506
Merged
Overview
Commits
1
Changes
View On GitHub

CUDA: use min compute capability of GPUs actually used #2506

JohannesGaessler merged 1 commit into ggml-org:master from cebtenzzre:better-min-cap
cebtenzzre
cebtenzzre CUDA: use min compute capability of GPUs actually used
c1320fd5
JohannesGaessler
JohannesGaessler approved these changes on 2023-08-04
JohannesGaessler JohannesGaessler merged 4329d1ac into master 3 years ago

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