ci : add test-llama-archs tensor split for Metal - #27598
Merged
Merged
Conversation
Run test-llama-archs with 1 to 4 GGML_METAL_DEVICES, mirroring the existing CUDA runs, and dispatch the job unconditionally since the per-backend guards now decide what to run. Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731
github-actions
Bot
added
the
devops
ggerganov
marked this pull request as ready for review
August 23, 2026 12:35
nikwen
approved these changes
Aug 23, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
Extends the
test_llama_archs_tensor_splitCI job to also runtest-llama-archswith 1 to 4GGML_METAL_DEVICES, mirroring the existing CUDA runs.GGML_METAL_DEVICESsimulates virtual Metal devices, enabling the multi-device tensor-split path to be exercised on Metal.The job is now dispatched unconditionally; the per-backend guards (
GG_BUILD_CUDA/GG_BUILD_METAL) inside the function decide which tests actually run, so CUDA-only, Metal-only, and non-GPU builds all behave correctly.Run: https://github.com/ggml-org/llama.cpp/actions/runs/32638102323/job/97190774015
Additional information
GG_BUILD_CUDAcheck was removed since it is now redundant with the internal guards.Requirements