mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-25 22:21:14 +02:00

Files

T

History

Georgi Gerganov 95b8e33e16 ci : add test-llama-archs tensor split for Metal (#27598 )

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

2026-08-23 15:57:07 +03:00

README-MUSA.md

musa: upgrade musa sdk to 4.3.0 (#16240 )

2025-09-26 02:56:38 +02:00

README.md

ci : migrate ggml ci to self-hosted runners (#16116 )

2025-09-21 16:50:45 +03:00

run.sh

ci : add test-llama-archs tensor split for Metal (#27598 )

2026-08-23 15:57:07 +03:00

README.md

CI

This CI implements heavy-duty workflows that run on self-hosted runners. Typically the purpose of these workflows is to cover hardware configurations that are not available from Github-hosted runners and/or require more computational resource than normally available.

It is a good practice, before publishing changes to execute the full CI locally on your machine. For example:

mkdir tmp

# CPU-only build
bash ./ci/run.sh ./tmp/results ./tmp/mnt

# with CUDA support
GG_BUILD_CUDA=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt

# with SYCL support
source /opt/intel/oneapi/setvars.sh
GG_BUILD_SYCL=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt

# with MUSA support
GG_BUILD_MUSA=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt

# etc.

Adding self-hosted runners

Add a self-hosted ggml-ci workflow to .github/workflows/build.yml with an appropriate label
Request a runner token from ggml-org (for example, via a comment in the PR or email)
Set-up a machine using the received token (docs)
Optionally update ci/run.sh to build and run on the target platform by gating the implementation with a GG_BUILD_... env