|
|
@@ -16,11 +16,6 @@ concurrency:
|
|
|
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
|
|
|
cancel-in-progress: true
|
|
|
|
|
|
-# Fine-grant permission
|
|
|
-# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
|
|
|
-permissions:
|
|
|
- contents: write # for creating release
|
|
|
-
|
|
|
env:
|
|
|
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
|
|
|
CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON"
|
|
|
@@ -416,28 +411,27 @@ jobs:
|
|
|
CURL_PATH: ${{ steps.get_libcurl.outputs.curl_path }}
|
|
|
run: |
|
|
|
cp $env:CURL_PATH\bin\libcurl-x64.dll .\build\bin\Release\libcurl-x64.dll
|
|
|
- 7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\*
|
|
|
+ 7z a llama-${{ steps.tag.outputs.name }}-bin-win-cuda${{ matrix.cuda }}-x64.zip .\build\bin\Release\*
|
|
|
|
|
|
- name: Upload artifacts
|
|
|
uses: actions/upload-artifact@v4
|
|
|
with:
|
|
|
- path: llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip
|
|
|
- name: llama-bin-win-cu${{ matrix.cuda }}-x64.zip
|
|
|
+ path: llama-${{ steps.tag.outputs.name }}-bin-win-cuda${{ matrix.cuda }}-x64.zip
|
|
|
+ name: llama-bin-win-cuda${{ matrix.cuda }}-x64.zip
|
|
|
|
|
|
- name: Copy and pack Cuda runtime
|
|
|
- if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
|
|
|
run: |
|
|
|
echo "Cuda install location: ${{ env.CUDA_PATH }}"
|
|
|
$dst='.\build\bin\cudart\'
|
|
|
robocopy "${{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 $dst\*
|
|
|
+ 7z a cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip $dst\*
|
|
|
|
|
|
- name: Upload Cuda runtime
|
|
|
uses: actions/upload-artifact@v4
|
|
|
with:
|
|
|
- path: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip
|
|
|
- name: cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip
|
|
|
+ path: cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip
|
|
|
+ name: cudart-llama-bin-win-cuda${{ matrix.cuda }}-x64.zip
|
|
|
|
|
|
windows-sycl:
|
|
|
runs-on: windows-latest
|
|
|
@@ -646,6 +640,11 @@ jobs:
|
|
|
release:
|
|
|
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
|
|
|
|
|
|
+ # Fine-grant permission
|
|
|
+ # https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
|
|
|
+ permissions:
|
|
|
+ contents: write # for creating release
|
|
|
+
|
|
|
runs-on: ubuntu-latest
|
|
|
|
|
|
needs:
|