Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

GGML_SYCL_FORCE_MMQ and SYCL_USE_XMX #12888

Open
Finalstar82 opened this issue Feb 24, 2025 · 0 comments
Open

GGML_SYCL_FORCE_MMQ and SYCL_USE_XMX #12888

Finalstar82 opened this issue Feb 24, 2025 · 0 comments
Labels
user issue

Comments

@Finalstar82
Copy link

I'm running the ipex-llm provide ollama on intel core ultra 7. when input ollama list I got below information in the Powershell

ggml_sycl_init: GGML_SYCL_FORCE_MMQ: no
ggml_sycl_init: SYCL_USE_XMX: yes
ggml_sycl_init: found 1 SYCL devices:

I'm curious that what is GGML_SYCL_FORCE_MMQ it looks like a similar accelerating tech as SYCL_USE_XMX.
Can we set the GGML_SYCL_FORCE_MMQ: yes?
I read other pages console output log, mostly are set GGML_SYCL_FORCE_MMQ: no . Is there any reason not enable this feature ?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
user issue
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@qiuxin2012 @Finalstar82