Skip to content

Conversation

@richiejp
Copy link
Collaborator

@richiejp richiejp commented Apr 3, 2025

  • chore(sycl): Update oneapi to 2025:1
  • fix(sycl): Pass -fsycl flag as workaround
  • fix(build): Speed up llama build by using all CPUs

Description

This PR fixes #4905

Notes for Reviewers

This is a hacky workaround, there is probably an issue with llama.cpp's build process or we are not calling cmake correctly.

The -fsycl should be set by llama.cpp's cmake lists file, but it appears that doesn't happen.

Signed commits

  • Yes, I signed my commits.

richiejp added 3 commits April 3, 2025 10:24
Signed-off-by: Richard Palethorpe <io@richiejp.com>
-fsycl should be set by llama.cpp's cmake file, but something goes wrong
and it doesn't appear to get added

Signed-off-by: Richard Palethorpe <io@richiejp.com>
Signed-off-by: Richard Palethorpe <io@richiejp.com>
@netlify
Copy link

netlify bot commented Apr 3, 2025

Deploy Preview for localai ready!

Name Link
🔨 Latest commit 3eab600
🔍 Latest deploy log https://app.netlify.com/sites/localai/deploys/67ee555210cbbb0008255c6c
😎 Deploy Preview https://deploy-preview-5115--localai.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify site configuration.

@richiejp richiejp changed the title Fix sycl kernel not found error by forcing -fsycl fix(sycl): kernel not found error by forcing -fsycl Apr 3, 2025
@mudler mudler merged commit d2cf8ef into mudler:master Apr 3, 2025
21 of 24 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

latest-aio-gpu-intel-f32 docker not working on the arc a750

2 participants