llama.cpp
Optimize Vulkan backend for better CPU performance and less GPU synchronization overhead.
#8943

Merged

Optimize Vulkan backend for better CPU performance and less GPU synchronization overhead. #8943

0cc4m merged 2 commits into ggml-org:master from mtavenrath:vulkan_perf

Optimize Vulkan backend for better CPU performance and less GPU synch…

af3cba04

github-actions added Vulkan

github-actions added ggml

mofosyne added performance

mofosyne added Review Complexity : Low

0cc4m assigned

0cc4m 1 year ago

0cc4m commented on 2024-08-10

Fix small typo

b2f9d224

0cc4m approved these changes on 2024-08-11

0cc4m merged 7c5bfd57 into master 1 year ago

Reviewers

0cc4m

Assignees

0cc4m

Labels

performance Vulkan Review Complexity : Low ggml

Milestone

No milestone