devops: kleidiai: provide KleidiAI-Enabled ARM Release Artifact (#21259)
* Unified macOS release setup with strategy-matrix block * Added KleidiAI arm64 macOS release definition Change-Id: I05520889ffc646488a178d06817a17f29274465a Signed-off-by: Martin Klacer <martin.klacer@arm.com>
This commit is contained in:
Martin Klacer
GitHub
parent
c5ce4bc227
commit
5c4aae66e1
|
|
@ -36,8 +36,26 @@ env:
|
|||
CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON"
|
||||
|
||||
jobs:
|
||||
macOS-arm64:
|
||||
runs-on: macos-14
|
||||
macOS-cpu:
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- build: 'arm64'
|
||||
arch: 'arm64'
|
||||
os: macos-14
|
||||
defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON"
|
||||
- build: 'arm64-kleidiai'
|
||||
arch: 'arm64'
|
||||
os: macos-14
|
||||
defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DGGML_CPU_KLEIDIAI=ON"
|
||||
- build: 'x64'
|
||||
arch: 'x64'
|
||||
os: macos-15-intel
|
||||
# Metal is disabled on x64 due to intermittent failures with Github runners not having a GPU:
|
||||
# https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313
|
||||
defines: "-DGGML_METAL=OFF -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3"
|
||||
|
||||
runs-on: ${{ matrix.os }}
|
||||
|
||||
steps:
|
||||
- name: Clone
|
||||
|
|
@ -49,7 +67,7 @@ jobs:
|
|||
- name: ccache
|
||||
uses: ggml-org/ccache-action@v1.2.21
|
||||
with:
|
||||
key: macOS-latest-arm64
|
||||
key: macOS-latest-${{ matrix.arch }}
|
||||
evict-old-files: 1d
|
||||
|
||||
- name: Build
|
||||
|
|
@ -57,13 +75,11 @@ jobs:
|
|||
run: |
|
||||
sysctl -a
|
||||
cmake -B build \
|
||||
${{ matrix.defines }} \
|
||||
-DCMAKE_INSTALL_RPATH='@loader_path' \
|
||||
-DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \
|
||||
-DLLAMA_FATAL_WARNINGS=ON \
|
||||
-DLLAMA_BUILD_BORINGSSL=ON \
|
||||
-DGGML_METAL_USE_BF16=ON \
|
||||
-DGGML_METAL_EMBED_LIBRARY=ON \
|
||||
-DGGML_RPC=ON \
|
||||
${{ env.CMAKE_ARGS }}
|
||||
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
|
||||
|
||||
|
|
@ -75,61 +91,13 @@ jobs:
|
|||
id: pack_artifacts
|
||||
run: |
|
||||
cp LICENSE ./build/bin/
|
||||
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.tar.gz -s ",./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
|
||||
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-macos-${{ matrix.build }}.tar.gz -s ",./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
|
||||
|
||||
- name: Upload artifacts
|
||||
uses: actions/upload-artifact@v6
|
||||
with:
|
||||
path: llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.tar.gz
|
||||
name: llama-bin-macos-arm64.tar.gz
|
||||
|
||||
macOS-x64:
|
||||
runs-on: macos-15-intel
|
||||
|
||||
steps:
|
||||
- name: Clone
|
||||
id: checkout
|
||||
uses: actions/checkout@v6
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: ccache
|
||||
uses: ggml-org/ccache-action@v1.2.21
|
||||
with:
|
||||
key: macOS-latest-x64
|
||||
evict-old-files: 1d
|
||||
|
||||
- name: Build
|
||||
id: cmake_build
|
||||
run: |
|
||||
sysctl -a
|
||||
# Metal is disabled due to intermittent failures with Github runners not having a GPU:
|
||||
# https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313
|
||||
cmake -B build \
|
||||
-DCMAKE_INSTALL_RPATH='@loader_path' \
|
||||
-DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \
|
||||
-DLLAMA_FATAL_WARNINGS=ON \
|
||||
-DLLAMA_BUILD_BORINGSSL=ON \
|
||||
-DGGML_METAL=OFF \
|
||||
-DGGML_RPC=ON \
|
||||
-DCMAKE_OSX_DEPLOYMENT_TARGET=13.3
|
||||
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
|
||||
|
||||
- name: Determine tag name
|
||||
id: tag
|
||||
uses: ./.github/actions/get-tag-name
|
||||
|
||||
- name: Pack artifacts
|
||||
id: pack_artifacts
|
||||
run: |
|
||||
cp LICENSE ./build/bin/
|
||||
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-macos-x64.tar.gz -s ",./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
|
||||
|
||||
- name: Upload artifacts
|
||||
uses: actions/upload-artifact@v6
|
||||
with:
|
||||
path: llama-${{ steps.tag.outputs.name }}-bin-macos-x64.tar.gz
|
||||
name: llama-bin-macos-x64.tar.gz
|
||||
path: llama-${{ steps.tag.outputs.name }}-bin-macos-${{ matrix.build }}.tar.gz
|
||||
name: llama-bin-macos-${{ matrix.build }}.tar.gz
|
||||
|
||||
ubuntu-cpu:
|
||||
strategy:
|
||||
|
|
@ -1003,8 +971,7 @@ jobs:
|
|||
- ubuntu-cpu
|
||||
- ubuntu-vulkan
|
||||
- ubuntu-24-openvino
|
||||
- macOS-arm64
|
||||
- macOS-x64
|
||||
- macOS-cpu
|
||||
- ios-xcode-build
|
||||
- openEuler-cann
|
||||
|
||||
|
|
@ -1079,6 +1046,7 @@ jobs:
|
|||
|
||||
**macOS/iOS:**
|
||||
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.tar.gz)
|
||||
- [macOS Apple Silicon (arm64, KleidiAI enabled)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-arm64-kleidiai.tar.gz)
|
||||
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-x64.tar.gz)
|
||||
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-xcframework.zip)
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue