Skip to content

Conversation

@qnixsynapse
Copy link
Collaborator

Reverts #9088;

Seems to cause a performance regression in some quantized models by never using the mmvq path.

cc: @airMeng @NeoZhangJianyu

@github-actions github-actions bot added ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language labels Sep 21, 2024
@airMeng airMeng merged commit e62e978 into ggml-org:master Sep 23, 2024
53 checks passed
@qnixsynapse qnixsynapse deleted the revert-9088-sycl-fallback-mmvq branch September 23, 2024 04:03
dsx1986 pushed a commit to dsx1986/llama.cpp that referenced this pull request Oct 29, 2024
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 15, 2024
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants