Merge pull request #795 from SciSharp/monsky_temp_pr_branch

Add the github build actions for Vulkan

.github/workflows/compile.yml

@@ -100,13 +100,86 @@ jobs:
           path: .\build\bin\Release\llava_shared.dll
           name: llava-bin-win-${{ matrix.build }}-x64.dll
 
+  compile-vulkan:
+      name: Compile (vulkan) - ${{ matrix.os }}
+      strategy:
+          fail-fast: false
+          matrix:
+              os: [
+                  ubuntu-22.04,
+                  windows-latest
+              ]
+      env:
+          VULKAN_VERSION: 1.3.261.1
+      runs-on: ${{ matrix.os }}
+      steps:
+          - name: Clone
+            id: checkout
+            uses: actions/checkout@v4
+            with:
+                repository: ggerganov/llama.cpp
+
+          - name: Download dependencies - Linux
+            if: ${{ matrix.os == 'ubuntu-22.04' }}
+            run: |
+                wget -qO- https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo tee /etc/apt/trusted.gpg.d/lunarg.asc
+                sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list http://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list
+                sudo apt update
+                sudo apt install vulkan-sdk
+          - name: Download dependencies - Windows
+            id: get_vulkan
+            if: ${{ matrix.os == 'windows-latest' }}
+            run: |
+                curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/VulkanSDK-${env:VULKAN_VERSION}-Installer.exe"
+                & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
+                Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
+                Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"
+          - name: Build
+            id: cmake_build
+            if: ${{ matrix.os == 'windows-latest' }}
+            run: |
+                mkdir build
+                cd build
+                cmake .. ${{ env.COMMON_DEFINE }} -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/vulkan"
+                cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
+                #copy $env:RUNNER_TEMP/clblast/lib/clblast.dll .\bin\Release\clblast.dll
+                # # We should probably generate a sha256 sum in a file, and use that.
+                # echo "78a8c98bcb2efe1a63318d901ab204d9ba96c3b29707b4ce0c4240bdcdc698d6  ./bin/Release/clblast.dll" >> tmp
+                # sha256sum -c tmp || exit 255
+                # rm tmp
+                ls -R
+          - name: Build
+            if: ${{ matrix.os == 'ubuntu-22.04' }}
+            run: |
+                mkdir build
+                cd build
+                cmake .. ${{ env.COMMON_DEFINE }} -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_VULKAN=ON -DBUILD_SHARED_LIBS=ON
+                cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
+                # if we ever want to pull libvulkan.so back into the packages, just uncomment this line, and the one below for the upload
+                # cp $(ldconfig -p | grep libvulkan.so | tail -n 1 | cut -d ' ' -f 4) ./
+                ls -R
+          - name: Upload artifacts (Windows)
+            if: ${{ matrix.os == 'windows-latest' }}
+            uses: actions/upload-artifact@v4
+            with:
+                path: |
+                    .\build\bin\Release\llama.dll
+                name: llama-bin-win-vulkan-x64.dll
+          - name: Upload artifacts (linux)
+            if: ${{ matrix.os == 'ubuntu-22.04' }}
+            uses: actions/upload-artifact@v4
+            with:
+                path: |
+                    ./build/libllama.so
+                name: llama-bin-linux-vulkan-x64.so
+
   compile-cublas:
     name: Compile (cublas)
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-20.04, windows-latest]
-        cuda: ['12.1.0', '11.7.1']
+        os: [ubuntu-20.04, windows-2019]
+        cuda: ['12.2.0', '11.7.1']
     runs-on: ${{ matrix.os }}
     steps:
       - name: Clone
@@ -117,15 +190,15 @@ jobs:
           fetch-depth: 0
           ref: '${{ github.event.inputs.llama_cpp_commit }}'
 
-      - uses: Jimver/[email protected].14
+      - uses: Jimver/[email protected].15
         if: runner.os == 'Windows'
         id: cuda-toolkit-windows
         with:
           cuda: ${{ matrix.cuda }}
           method: 'network'
           sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
 
-      - uses: Jimver/[email protected].14
+      - uses: Jimver/[email protected].15
         if: runner.os == 'Linux'
         id: cuda-toolkit-linux
         with:
@@ -138,18 +211,18 @@ jobs:
         run: |
           mkdir build
           cd build
-          cmake .. ${{ env.COMMON_DEFINE }} -DLLAMA_CUBLAS=ON
+          cmake .. ${{ env.COMMON_DEFINE }} -DLLAMA_CUDA=ON
           cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
           ls -R
 
       - name: Upload artifacts (Windows)
-        if: ${{ matrix.os == 'windows-latest' }}
+        if: ${{ matrix.os == 'windows-2019' }}
         uses: actions/upload-artifact@v4
         with:
           path: .\build\bin\Release\llama.dll
           name: llama-bin-win-cublas-cu${{ matrix.cuda }}-x64.dll
       - name: Upload llava artifacts (Windows)
-        if: ${{ matrix.os == 'windows-latest' }}
+        if: ${{ matrix.os == 'windows-2019' }}
         uses: actions/upload-artifact@v4
         with:
           path: .\build\bin\Release\llava_shared.dll
@@ -223,7 +296,8 @@ jobs:
       "compile-linux",
       "compile-macos",
       "compile-windows",
-      "compile-cublas"
+      "compile-cublas",
+      "compile-vulkan"
     ]
     steps:      
       - uses: actions/download-artifact@v4
@@ -234,7 +308,7 @@ jobs:
       - name: Rearrange Files
         run: |
           # Make all directories at once
-          mkdir --parents deps/{avx,avx2,avx512,osx-arm64,osx-x64,osx-x64-rosetta2,cu11.7.1,cu12.1.0}
+          mkdir --parents deps/{avx,avx2,avx512,osx-arm64,osx-x64,osx-x64-rosetta2,cu11.7.1,cu12.2.0,vulkan}
 
           cp artifacts/llama-bin-linux-noavx-x64.so/libllama.so  deps/libllama.so
           cp artifacts/llama-bin-linux-avx-x64.so/libllama.so    deps/avx/libllama.so
@@ -273,12 +347,14 @@ jobs:
           cp artifacts/llama-bin-linux-cublas-cu11.7.1-x64.so/libllama.so deps/cu11.7.1/libllama.so
           cp artifacts/llava-bin-linux-cublas-cu11.7.1-x64.so/libllava_shared.so deps/cu11.7.1/libllava_shared.so
           
-          cp artifacts/llama-bin-win-cublas-cu12.1.0-x64.dll/llama.dll    deps/cu12.1.0/llama.dll
-          cp artifacts/llava-bin-win-cublas-cu12.1.0-x64.dll/llava_shared.dll    deps/cu12.1.0/llava_shared.dll
+          cp artifacts/llama-bin-win-cublas-cu12.2.0-x64.dll/llama.dll    deps/cu12.2.0/llama.dll
+          cp artifacts/llava-bin-win-cublas-cu12.2.0-x64.dll/llava_shared.dll    deps/cu12.2.0/llava_shared.dll
 
-          cp artifacts/llama-bin-linux-cublas-cu12.1.0-x64.so/libllama.so deps/cu12.1.0/libllama.so
-          cp artifacts/llava-bin-linux-cublas-cu12.1.0-x64.so/libllava_shared.so deps/cu12.1.0/libllava_shared.so
+          cp artifacts/llama-bin-linux-cublas-cu12.2.0-x64.so/libllama.so deps/cu12.2.0/libllama.so
+          cp artifacts/llava-bin-linux-cublas-cu12.2.0-x64.so/libllava_shared.so deps/cu12.2.0/libllava_shared.so
 
+          cp artifacts/llama-bin-win-vulkan-x64.dll/llama.dll deps/vulkan/
+          cp artifacts/llama-bin-linux-vulkan-x64.so/libllama.so deps/vulkan/
 
       - name: Upload artifacts
         uses: actions/upload-artifact@v4