mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 06:39:25 +01:00
ci : faster CUDA toolkit installation method and use ccache (#10537)
* ci : faster CUDA toolkit installation method and use ccache * remove fetch-depth * only pack CUDA runtime on master
This commit is contained in:
Diego Devesa
GitHub
parent
9e2301f4a4
commit
46c69e0e75
117
.github/workflows/build.yml
vendored
117
.github/workflows/build.yml
vendored
@ -892,12 +892,12 @@ jobs:
|
|||||||
cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=89-real -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined -DLLAMA_FATAL_WARNINGS=ON
|
cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=89-real -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined -DLLAMA_FATAL_WARNINGS=ON
|
||||||
cmake --build build
|
cmake --build build
|
||||||
|
|
||||||
windows-latest-cmake-cuda:
|
windows-2019-cmake-cuda:
|
||||||
runs-on: windows-latest
|
runs-on: windows-2019
|
||||||
|
|
||||||
strategy:
|
strategy:
|
||||||
matrix:
|
matrix:
|
||||||
cuda: ['12.6.2']
|
cuda: ['12.4', '11.7']
|
||||||
build: ['cuda']
|
build: ['cuda']
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
@ -905,13 +905,66 @@ jobs:
|
|||||||
id: checkout
|
id: checkout
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
|
|
||||||
- name: Install CUDA toolkit
|
- name: Install Cuda Toolkit 11.7
|
||||||
id: cuda-toolkit
|
if: ${{ matrix.cuda == '11.7' }}
|
||||||
uses: Jimver/cuda-toolkit@v0.2.19
|
run: |
|
||||||
|
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7"
|
||||||
|
choco install unzip -y
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-11.7.99-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-11.7.99-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-11.7.99-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-11.7.4.6-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-11.7.91-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-11.7.91-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-11.7.101-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-11.7.91-archive.zip"
|
||||||
|
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7"
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cudart-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvcc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvrtc-windows-x86_64-11.7.99-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libcublas-windows-x86_64-11.7.4.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvtx-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\visual_studio_integration-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_nvprof-windows-x86_64-11.7.101-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\cuda_cccl-windows-x86_64-11.7.91-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" /E /I /H /Y
|
||||||
|
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||||
|
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||||
|
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
|
||||||
|
echo "CUDA_PATH_V11_7=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
|
||||||
|
|
||||||
|
- name: Install Cuda Toolkit 12.4
|
||||||
|
if: ${{ matrix.cuda == '12.4' }}
|
||||||
|
run: |
|
||||||
|
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
|
||||||
|
choco install unzip -y
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip"
|
||||||
|
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip"
|
||||||
|
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
|
||||||
|
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||||
|
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||||
|
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
|
||||||
|
echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
|
||||||
|
|
||||||
|
- name: Install ccache
|
||||||
|
uses: hendrikmuhs/ccache-action@v1.2
|
||||||
with:
|
with:
|
||||||
cuda: ${{ matrix.cuda }}
|
key: ${{ github.job }}-${{ matrix.cuda }}-${{ matrix.build }}
|
||||||
method: 'network'
|
|
||||||
sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
|
|
||||||
|
|
||||||
- name: Install Ninja
|
- name: Install Ninja
|
||||||
id: install_ninja
|
id: install_ninja
|
||||||
@ -922,44 +975,12 @@ jobs:
|
|||||||
id: cmake_build
|
id: cmake_build
|
||||||
shell: cmd
|
shell: cmd
|
||||||
run: |
|
run: |
|
||||||
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat"
|
call "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\VC\Auxiliary\Build\vcvars64.bat"
|
||||||
cmake -S . -B build -G "Ninja Multi-Config" -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DBUILD_SHARED_LIBS=ON -DGGML_RPC=ON -DCMAKE_CUDA_ARCHITECTURES=89-real
|
cmake -S . -B build -G "Ninja Multi-Config" -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_CUDA=ON -DBUILD_SHARED_LIBS=ON -DGGML_RPC=ON
|
||||||
cmake --build build --config Release -t ggml-cuda
|
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
|
||||||
|
cmake --build build --config Release -j %NINJA_JOBS% -t ggml
|
||||||
cmake --build build --config Release
|
cmake --build build --config Release
|
||||||
|
|
||||||
windows-2019-cmake-cuda:
|
|
||||||
runs-on: windows-2019
|
|
||||||
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
||||||
|
|
||||||
strategy:
|
|
||||||
matrix:
|
|
||||||
cuda: ['12.2.0', '11.7.1']
|
|
||||||
build: ['cuda']
|
|
||||||
|
|
||||||
steps:
|
|
||||||
- name: Clone
|
|
||||||
id: checkout
|
|
||||||
uses: actions/checkout@v4
|
|
||||||
with:
|
|
||||||
fetch-depth: 0
|
|
||||||
|
|
||||||
- name: Install CUDA toolkit
|
|
||||||
id: cuda-toolkit
|
|
||||||
uses: Jimver/cuda-toolkit@v0.2.15
|
|
||||||
with:
|
|
||||||
cuda: ${{ matrix.cuda }}
|
|
||||||
method: 'network'
|
|
||||||
sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
|
|
||||||
|
|
||||||
- name: Build
|
|
||||||
id: cmake_build
|
|
||||||
run: |
|
|
||||||
mkdir build
|
|
||||||
cd build
|
|
||||||
cmake .. -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_CUDA=ON -DBUILD_SHARED_LIBS=ON -DGGML_RPC=ON
|
|
||||||
cmake --build . --config Release -j $((${env:NUMBER_OF_PROCESSORS} - 1)) -t ggml
|
|
||||||
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
|
|
||||||
|
|
||||||
- name: Determine tag name
|
- name: Determine tag name
|
||||||
id: tag
|
id: tag
|
||||||
shell: bash
|
shell: bash
|
||||||
@ -987,10 +1008,12 @@ jobs:
|
|||||||
name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip
|
name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip
|
||||||
|
|
||||||
- name: Copy and pack Cuda runtime
|
- name: Copy and pack Cuda runtime
|
||||||
|
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
||||||
run: |
|
run: |
|
||||||
echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
|
echo "Cuda install location: ${{ env.CUDA_PATH }}"
|
||||||
$dst='.\build\bin\cudart\'
|
$dst='.\build\bin\cudart\'
|
||||||
robocopy "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
|
robocopy "${{env.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
|
||||||
|
robocopy "${{env.CUDA_PATH}}\lib" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
|
||||||
7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\*
|
7z a cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\*
|
||||||
|
|
||||||
- name: Upload Cuda runtime
|
- name: Upload Cuda runtime
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user