Skip to content

Conversation

netrunnereve
Copy link
Collaborator

@netrunnereve netrunnereve commented Sep 22, 2025

This basically lets me run the x64 ci on local forks using the standard Github machines. Currently this takes around 4 minutes for the low perf run and 15 minutes for the high perf run with a filled ccache.

I'm leaving this as a draft for now to see if there's interest in doing this over using our self hosted machines.

@github-actions github-actions bot added the devops improvements to build systems and github actions label Sep 22, 2025
fix test-quantize-perf just like #12306
@github-actions github-actions bot added the testing Everything test related label Sep 23, 2025
@netrunnereve
Copy link
Collaborator Author

I added the Arm machines as well, though that one's for some reason failing on rerank score 2 when running the rerank model.

@netrunnereve netrunnereve changed the title ci: run the x64 ci on the github machines instead ci: run the x64 and arm ci on the github machines instead Sep 23, 2025
@ggerganov
Copy link
Member

I added the Arm machines as well, though that one's for some reason failing on rerank score 2 when running the rerank model.

My best guess is that the SVE path has a bug. But I don't have a machine to test this.

If we resolve the failing workflow, we can decommission the 4 self-hosted CPU runners in favor of Github-hosted runners.

@ggerganov
Copy link
Member

Looks like it works correct without SVE.

@netrunnereve
Copy link
Collaborator Author

Yeah it looks like a sve issue as it passes fine on the self hosted machine with no sve, and it's passing here as well with sve manually turned off. I don't have an Arm sve machine either so I can't really dig deeper into why this is failing.

@netrunnereve netrunnereve marked this pull request as ready for review September 24, 2025 01:32
Copy link
Member

@ggerganov ggerganov left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In this case, I think it is worth adding 2 Arm workflows:

  • ggml-ci-arm64-cpu-high-perf
  • ggml-ci-arm64-cpu-high-perf-sve

The second one will have SVE enabled and will fail for the time being, but we will be aware of the issue and fix it later.

@ggerganov ggerganov merged commit bee378e into ggml-org:master Sep 25, 2025
61 of 66 checks passed
@netrunnereve netrunnereve deleted the ci branch September 25, 2025 14:30
pwilkin pushed a commit to pwilkin/llama.cpp that referenced this pull request Sep 25, 2025
…6183)

* run the x64 ci on regular machines

* set up the same thing for arm

fix test-quantize-perf just like ggml-org#12306

* try to disable sve

* add another sve run
struct pushed a commit to struct/llama.cpp that referenced this pull request Sep 26, 2025
…6183)

* run the x64 ci on regular machines

* set up the same thing for arm

fix test-quantize-perf just like ggml-org#12306

* try to disable sve

* add another sve run
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
devops improvements to build systems and github actions testing Everything test related
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants