Daniel Bevenius
e216f4ec87
This commit extracts all apple jobs except for macos-latest-arm64 into a new daily workflow. The motivation for this is to reducd the load on the macos runners.
110 lines
3.1 KiB
YAML
110 lines
3.1 KiB
YAML
name: CI (apple)
|
|
|
|
on:
|
|
workflow_dispatch: # allows manual triggering
|
|
push:
|
|
branches:
|
|
- master
|
|
paths: [
|
|
'.github/workflows/build-apple.yml',
|
|
'**/CMakeLists.txt',
|
|
'**/.cmake',
|
|
'**/*.h',
|
|
'**/*.hpp',
|
|
'**/*.c',
|
|
'**/*.cpp',
|
|
'**/*.swift',
|
|
'**/*.m',
|
|
'**/*.metal'
|
|
]
|
|
|
|
pull_request:
|
|
types: [opened, synchronize, reopened]
|
|
paths: [
|
|
'.github/workflows/build-apple.yml',
|
|
'ggml/src/ggml-metal/**',
|
|
'ggml/src/ggml-rpc/**'
|
|
]
|
|
|
|
cache-mode: none
|
|
permissions:
|
|
contents: read
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
|
|
cancel-in-progress: true
|
|
|
|
env:
|
|
GGML_NLOOP: 3
|
|
GGML_N_THREADS: 1
|
|
GGML_SCHED_DEBUG_REALLOC: 1
|
|
LLAMA_ARG_LOG_COLORS: 1
|
|
LLAMA_ARG_LOG_PREFIX: 1
|
|
LLAMA_ARG_LOG_TIMESTAMPS: 1
|
|
|
|
jobs:
|
|
macos-latest-arm64:
|
|
runs-on: macos-latest
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v6
|
|
|
|
- name: ccache
|
|
uses: ggml-org/ccache-action@v1.2.24
|
|
with:
|
|
restore: false
|
|
save: false
|
|
|
|
- name: ccache-buckets-restore
|
|
uses: ./.github/actions/ccache-buckets
|
|
env:
|
|
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
|
|
with:
|
|
key: apple-arm64
|
|
folder: llama.cpp
|
|
hf_bucket: ggml-org/cache
|
|
|
|
- name: Build
|
|
id: cmake_build
|
|
run: |
|
|
sysctl -a
|
|
cmake -B build \
|
|
-DCMAKE_BUILD_RPATH="@loader_path" \
|
|
-DLLAMA_FATAL_WARNINGS=ON \
|
|
-DLLAMA_BUILD_BORINGSSL=ON \
|
|
-DGGML_METAL_EMBED_LIBRARY=OFF \
|
|
-DGGML_METAL_SHADER_DEBUG=ON \
|
|
-DGGML_RPC=ON \
|
|
-DCMAKE_OSX_DEPLOYMENT_TARGET=13.3
|
|
time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
|
|
|
|
- name: ccache-buckets-save
|
|
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
uses: ./.github/actions/ccache-buckets
|
|
env:
|
|
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
|
|
with:
|
|
key: apple-arm64
|
|
folder: llama.cpp
|
|
evict-old-files: 1d
|
|
hf_bucket: ggml-org/cache
|
|
save: true
|
|
|
|
- name: Check for leaks
|
|
run: |
|
|
cmd=(./build/bin/test-thread-safety -hf ggml-org/gemma-3-270m-qat-GGUF -ngl 99 -p "$(printf 'hello %.0s' {1..128})" -n 16 -c 512 -ub 32 -np 2 -t 2 -lv 1)
|
|
leaks -atExit -- "${cmd[@]}"
|
|
# Graphics devices are leaked by Metal in Apple code sometimes, so we ignore those leaks
|
|
OBJC_DEBUG_MISSING_POOLS=YES "${cmd[@]}" 2>&1 | awk '{ print } index($0, "autoreleased with no pool in place") && !/class [a-zA-Z0-9]+Device autoreleased/ { found = 1 } END { exit found }'
|
|
|
|
- name: Test
|
|
id: cmake_test
|
|
run: |
|
|
cd build
|
|
# Metal Paravirtual devices are difficult to support -> disable
|
|
# ref: https://github.com/ggml-org/llama.cpp/pull/19802#issuecomment-4013704023
|
|
ctest -L main -E "test-llama-archs|test-llama-context|test-speculative-rejection-sampling" --verbose --timeout 900
|
|
|