Skip to content

feat(swiftbuddy): MemPalace v1, native macOS theming, HF model manage… #38

feat(swiftbuddy): MemPalace v1, native macOS theming, HF model manage…

feat(swiftbuddy): MemPalace v1, native macOS theming, HF model manage… #38

Workflow file for this run

name: CI Pipeline
on:
push:
branches: [main]
pull_request:
branches: [main]
concurrency:
group: ci-${{ github.ref }}
cancel-in-progress: true
jobs:
ci:
runs-on: macos-15
timeout-minutes: 40
strategy:
fail-fast: false
matrix:
modality: [server, vision, audio]
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Install Metal Toolchain
run: xcodebuild -downloadComponent MetalToolchain || true
- name: Cache Swift packages
uses: actions/cache@v4
with:
path: .build
# Key includes product name so any rename (e.g. mlx-server→SwiftLM)
# automatically busts the cache and prevents stale PCH errors.
key: ${{ runner.os }}-spm-SwiftLM-v2-${{ hashFiles('Package.resolved') }}
restore-keys: |
${{ runner.os }}-spm-SwiftLM-v2-
- name: Clear stale module cache
# Prevents: "PCH was compiled with module cache path '…mlx-server…'
# but the path is currently '…SwiftLM…'" after repo rename.
run: find .build -type d -name ModuleCache -exec rm -rf {} + 2>/dev/null || true
- name: Resolve dependencies
run: swift package resolve
- name: Build (Release)
run: swift build -c release
- name: Verify binary
run: |
ls -lh .build/release/SwiftLM
file .build/release/SwiftLM
- name: TurboQuant unit tests
run: |
# Compile and run standalone C++ unit tests for the TurboQuant
# KV cache compression algorithm (ported from TheTom/llama-cpp-turboquant).
# Tests: centroids, WHT self-inverse, rotation orthogonality,
# 3-bit pack/unpack, V-cache SNR, K-cache IP SNR, fp16 round-trip.
clang++ -std=c++17 -O2 -o /tmp/tq_test tests/test_turbo_quant.cpp
/tmp/tq_test
- name: Build Test Harness
run: swift build --build-tests
- name: Install MLX Metal library
run: |
python3 -m venv /tmp/mlx_venv
/tmp/mlx_venv/bin/pip install --quiet mlx
# Inject metallib for production e2e runner
cp /tmp/mlx_venv/lib/python*/site-packages/mlx/lib/mlx.metallib .build/release/
# Distribute metallib exclusively to XCTest bundles so it satisfies memory.cpp current_binary_dir() constraints natively.
find .build -type d -name "MacOS" -exec cp /tmp/mlx_venv/lib/python*/site-packages/mlx/lib/mlx.metallib {}/ \;
- name: SwiftBuddy Tests (MemPalace & Lifecycle)
run: swift test --skip-build --filter SwiftBuddyTests --disable-swift-testing
- name: Cache MLX model
uses: actions/cache@v4
with:
path: ~/.cache/huggingface
key: mlx-model-qwen2.5-0.5b-4bit
- name: Run E2E tests
env:
HF_HUB_DOWNLOAD_TIMEOUT: "600"
run: |
chmod +x tests/test-${{ matrix.modality }}.sh
# Retry up to 2 times for transient HuggingFace download failures
for attempt in 1 2 3; do
echo "Attempt $attempt of 3..."
if tests/test-${{ matrix.modality }}.sh .build/release/SwiftLM 15413; then
exit 0
fi
if [ "$attempt" -lt 3 ]; then
echo "Test failed, retrying in 10s..."
sleep 10
fi
done
echo "All attempts failed"
exit 1
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v4
with:
name: ci-test-logs
path: /tmp/SwiftLM-test-*.log
retention-days: 7