From 0c84583416bc443e714d7857e05081c47f869a53 Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Sun, 8 Oct 2023 18:57:42 +0700
Subject: [PATCH 1/9] feat(ci): init commit for windows with/ without GPU
 support

---
 .github/workflows/build.yml | 517 ++++++++++++++++++++++++------------
 1 file changed, 352 insertions(+), 165 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index ee9e9a2c8..cdd28a198 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -10,6 +10,7 @@ on:
   push:
     branches:
       - master
+      - 57-add-github-ci-cd-for-windows
     paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu']
   pull_request:
     types: [opened, synchronize, reopened]
@@ -19,211 +20,397 @@ env:
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
 
 jobs:
-  ubuntu-amd64-build:
-    runs-on: ubuntu-20.04
-    permissions:
-      contents: write
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: recursive
+  # ubuntu-amd64-build:
+  #   runs-on: ubuntu-20.04
+  #   permissions:
+  #     contents: write
+  #   steps:
+  #     - name: Clone
+  #       id: checkout
+  #       uses: actions/checkout@v3
+  #       with:
+  #         submodules: recursive
 
-      - name: Dependencies
-        id: depends
-        run: |
-          sudo apt-get update
-          sudo apt-get install build-essential gcc-8
+  #     - name: Dependencies
+  #       id: depends
+  #       run: |
+  #         sudo apt-get update
+  #         sudo apt-get install build-essential gcc-8
 
-      - name: Build
-        id: make_build
-        run: |
-          ./install_deps.sh
-          mkdir build && cd build
-          cmake ..
-          CC=gcc-8 make -j $(nproc)
-          ls -la
+  #     - name: Build
+  #       id: make_build
+  #       run: |
+  #         ./install_deps.sh
+  #         mkdir build && cd build
+  #         cmake ..
+  #         CC=gcc-8 make -j $(nproc)
+  #         ls -la
 
-      - name: Extract branch name
-        shell: bash
-        id: extract_branch
-        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
-      - name: Extract commit short SHA
-        id: extract_commit_id
-        run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
+  #     - name: Extract branch name
+  #       shell: bash
+  #       id: extract_branch
+  #       run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
+  #     - name: Extract commit short SHA
+  #       id: extract_commit_id
+  #       run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
 
-      - name: Package
-        shell: bash
-        run: |
-          mkdir -p nitro && mkdir -p nitro/config
-          cp config.json nitro/config/
-          cp build/nitro nitro/
-          zip -r nitro.zip nitro
+  #     - name: Package
+  #       shell: bash
+  #       run: |
+  #         mkdir -p nitro && mkdir -p nitro/config
+  #         cp config.json nitro/config/
+  #         cp build/nitro nitro/
+  #         zip -r nitro.zip nitro
 
-      - name: Upload binaries to release
-        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
-        uses: svenstaro/upload-release-action@v2
-        with:
-          repo_token: ${{ secrets.GITHUB_TOKEN }}
-          file: nitro.zip
-          asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-linux-amd64.zip
-          tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
-
-  ubuntu-amd64-cuda-build:
-    runs-on: linux-gpu
-    permissions:
-      contents: write
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: recursive
+  #     - name: Upload binaries to release
+  #       if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+  #       uses: svenstaro/upload-release-action@v2
+  #       with:
+  #         repo_token: ${{ secrets.GITHUB_TOKEN }}
+  #         file: nitro.zip
+  #         asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-linux-amd64.zip
+  #         tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
 
-      # - name: Dependencies
-      #   id: depends
-      #   run: |
-      #     sudo apt-get update
-      #     sudo apt-get install build-essential gcc-8 uuid-dev
+  # ubuntu-amd64-cuda-build:
+  #   runs-on: linux-gpu
+  #   permissions:
+  #     contents: write
+  #   steps:
+  #     - name: Clone
+  #       id: checkout
+  #       uses: actions/checkout@v3
+  #       with:
+  #         submodules: recursive
 
-      - name: Build
-        id: make_build
-        run: |
-          ./install_deps.sh
-          mkdir build && cd build
-          cmake -DLLAMA_CUBLAS=ON ..
-          CC=gcc-8 make -j $(nproc)
-          ls -la   
+  #     # - name: Dependencies
+  #     #   id: depends
+  #     #   run: |
+  #     #     sudo apt-get update
+  #     #     sudo apt-get install build-essential gcc-8 uuid-dev
 
-      - name: Extract branch name
-        shell: bash
-        id: extract_branch
-        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
+  #     - name: Build
+  #       id: make_build
+  #       run: |
+  #         ./install_deps.sh
+  #         mkdir build && cd build
+  #         cmake -DLLAMA_CUBLAS=ON ..
+  #         CC=gcc-8 make -j $(nproc)
+  #         ls -la   
 
-      - name: Extract commit short SHA
-        id: extract_commit_id
-        run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
+  #     - name: Extract branch name
+  #       shell: bash
+  #       id: extract_branch
+  #       run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
 
-      - name: Package
-        shell: bash
-        run: |
-          mkdir -p nitro && mkdir -p nitro/config
-          cp config.json nitro/config/
-          cp build/nitro nitro/
-          zip -r nitro.zip nitro
+  #     - name: Extract commit short SHA
+  #       id: extract_commit_id
+  #       run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
+
+  #     - name: Package
+  #       shell: bash
+  #       run: |
+  #         mkdir -p nitro && mkdir -p nitro/config
+  #         cp config.json nitro/config/
+  #         cp build/nitro nitro/
+  #         zip -r nitro.zip nitro
+
+  #     - name: Upload binaries to release
+  #       if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+  #       uses: svenstaro/upload-release-action@v2
+  #       with:
+  #         repo_token: ${{ secrets.GITHUB_TOKEN }}
+  #         file: nitro.zip
+  #         asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-linux-amd64-cuda.zip
+  #         tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
+
+  # macOS-M-build:
+  #   runs-on: mac-silicon
+  #   permissions:
+  #     contents: write
+  #   steps:
+  #     - name: Clone
+  #       id: checkout
+  #       uses: actions/checkout@v3
+  #       with:
+  #         submodules: recursive
+
+  #     - name: Dependencies
+  #       id: depends
+  #       continue-on-error: true
+  #       run: |
+  #         brew update
+  #         brew install cmake gcc@8
+
+  #     - name: Build
+  #       id: cmake_build
+  #       run: |
+  #         ./install_deps.sh
+  #         mkdir build && cd build
+  #         cmake .. 
+  #         CC=gcc-8 make -j $(nproc)
+  #         ls -la
+
+  #     - name: Extract branch name
+  #       shell: bash
+  #       id: extract_branch
+  #       run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
+  
+  #     - name: Extract commit short SHA
+  #       id: extract_commit_id
+  #       run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
+  
+  #     - name: Package
+  #       shell: bash
+  #       run: |
+  #         mkdir -p nitro && mkdir -p nitro/config
+  #         cp config.json nitro/config/
+  #         cp llama.cpp/ggml-metal.h nitro/
+  #         cp build/nitro nitro/
+  #         zip -r nitro.zip nitro
+
+  #     - name: Upload binaries to release
+  #       if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+  #       uses: svenstaro/upload-release-action@v2
+  #       with:
+  #         repo_token: ${{ secrets.GITHUB_TOKEN }}
+  #         file: nitro.zip
+  #         asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-mac-arm64.zip
+  #         tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
+
+  # macOS-Intel-build:
+  #   runs-on: macos-latest
+  #   permissions:
+  #     contents: write
+  #   steps:
+  #     - name: Clone
+  #       id: checkout
+  #       uses: actions/checkout@v3
+  #       with:
+  #         submodules: recursive
+
+  #     - name: Dependencies
+  #       id: depends
+  #       continue-on-error: true
+  #       run: |
+  #         brew update
+
+  #     - name: Build
+  #       id: cmake_build
+  #       run: |
+  #         ./install_deps.sh
+  #         mkdir build && cd build
+  #         cmake -DLLAMA_METAL=OFF .. 
+  #         CC=gcc-8 make -j $(nproc)
+  #         ls -la
+
+  #     - name: Extract branch name
+  #       shell: bash
+  #       id: extract_branch
+  #       run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
+    
+  #     - name: Extract commit short SHA
+  #       id: extract_commit_id
+  #       run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
+    
+  #     - name: Package
+  #       shell: bash
+  #       run: |
+  #         mkdir -p nitro && mkdir -p nitro/config
+  #         cp config.json nitro/config/
+  #         cp build/nitro nitro/
+  #         zip -r nitro.zip nitro
+
+  #     - name: Upload binaries to release
+  #       if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+  #       uses: svenstaro/upload-release-action@v2
+  #       with:
+  #         repo_token: ${{ secrets.GITHUB_TOKEN }}
+  #         file: nitro.zip
+  #         asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-mac-amd64.zip.zip
+  #         tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
+
+  windows-latest-cmake:
+    runs-on: windows-latest
+
+    env:
+      OPENBLAS_VERSION: 0.3.23
+      OPENCL_VERSION: 2023.04.17
+      CLBLAST_VERSION: 1.6.0
+
+    strategy:
+      matrix:
+        include:
+          - build: 'avx2'
+            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON'
+          - build: 'avx512'
+            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
+          - build: 'clblast'
+            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
+          - build: 'openblas'
+            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
 
-      - name: Upload binaries to release
-        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
-        uses: svenstaro/upload-release-action@v2
-        with:
-          repo_token: ${{ secrets.GITHUB_TOKEN }}
-          file: nitro.zip
-          asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-linux-amd64-cuda.zip
-          tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
-
-  macOS-M-build:
-    runs-on: mac-silicon
-    permissions:
-      contents: write
     steps:
       - name: Clone
         id: checkout
         uses: actions/checkout@v3
         with:
-          submodules: recursive
+          fetch-depth: 0
+
+      - name: Download OpenCL SDK
+        id: get_opencl
+        if: ${{ matrix.build == 'clblast' }}
+        run: |
+          curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip"
+          mkdir $env:RUNNER_TEMP/opencl
+          tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl
+
+      - name: Download CLBlast
+        id: get_clblast
+        if: ${{ matrix.build == 'clblast' }}
+        run: |
+          curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z"
+          curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE"
+          7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z
+          rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast
+          foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) {
+            $txt = Get-Content -Path $f -Raw
+            $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8
+          }
 
-      - name: Dependencies
-        id: depends
-        continue-on-error: true
+      - name: Download OpenBLAS
+        id: get_openblas
+        if: ${{ matrix.build == 'openblas' }}
         run: |
-          brew update
-          brew install cmake gcc@8
+          curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip"
+          curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE"
+          mkdir $env:RUNNER_TEMP/openblas
+          tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas
+          $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath)
+          $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim()))
+          $lib =  $(join-path $msvc 'bin\Hostx64\x64\lib.exe')
+          & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll
 
       - name: Build
         id: cmake_build
         run: |
-          ./install_deps.sh
-          mkdir build && cd build
-          cmake .. 
-          CC=gcc-8 make -j $(nproc)
-          ls -la
+          cmake --build ./build_deps/nitro_deps --config Release
+          mkdir build
+          cd build
+          cmake .. ${{ matrix.defines }}
+          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
 
-      - name: Extract branch name
-        shell: bash
-        id: extract_branch
-        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
-  
-      - name: Extract commit short SHA
-        id: extract_commit_id
-        run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
-  
-      - name: Package
+      - name: Add clblast.dll
+        id: add_clblast_dll
+        if: ${{ matrix.build == 'clblast' }}
+        run: |
+          cp $env:RUNNER_TEMP/clblast/lib/clblast.dll ./build/bin/Release
+          cp $env:RUNNER_TEMP/CLBlast.LICENSE.txt ./build/bin/Release/CLBlast-${env:CLBLAST_VERSION}.txt
+
+      - name: Add libopenblas.dll
+        id: add_libopenblas_dll
+        if: ${{ matrix.build == 'openblas' }}
+        run: |
+          cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll
+          cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt
+
+      - name: Determine tag name
+        id: tag
         shell: bash
         run: |
-          mkdir -p nitro && mkdir -p nitro/config
-          cp config.json nitro/config/
-          cp llama.cpp/ggml-metal.h nitro/
-          cp build/nitro nitro/
-          zip -r nitro.zip nitro
+          BUILD_NUMBER="$(git rev-list --count HEAD)"
+          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
+          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
+            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
+          else
+            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
+            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
+          fi
 
-      - name: Upload binaries to release
-        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
-        uses: svenstaro/upload-release-action@v2
+      - name: Pack artifacts
+        id: pack_artifacts
+        # if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        run: |
+          Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt
+          robocopy build_deps\_install\bin\zlib.dll $dst
+          robocopy build\bin\Release\llama.dll $dst
+          7z a nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\*
+
+      - name: Upload artifacts
+        # if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
         with:
-          repo_token: ${{ secrets.GITHUB_TOKEN }}
-          file: nitro.zip
-          asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-mac-arm64.zip
-          tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
-
-  macOS-Intel-build:
-    runs-on: macos-latest
-    permissions:
-      contents: write
+          path: |
+            nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip
+
+  windows-latest-cmake-cublas:
+    runs-on: windows-gpu
+
+    strategy:
+      matrix:
+        cuda: ['12.2.0', '11.7.1']
+        build: ['cublas']
+
     steps:
       - name: Clone
         id: checkout
         uses: actions/checkout@v3
         with:
-          submodules: recursive
+          fetch-depth: 0
 
-      - name: Dependencies
-        id: depends
-        continue-on-error: true
-        run: |
-          brew update
+      - uses: Jimver/cuda-toolkit@v0.2.11
+        id: cuda-toolkit
+        with:
+          cuda: ${{ matrix.cuda }}
+          method: 'network'
+          sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
 
       - name: Build
         id: cmake_build
         run: |
-          ./install_deps.sh
-          mkdir build && cd build
-          cmake -DLLAMA_METAL=OFF .. 
-          CC=gcc-8 make -j $(nproc)
-          ls -la
+          cmake --build ./build_deps/nitro_deps --config Release
+          mkdir build
+          cd build
+          cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
+          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
 
-      - name: Extract branch name
-        shell: bash
-        id: extract_branch
-        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
-    
-      - name: Extract commit short SHA
-        id: extract_commit_id
-        run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
-    
-      - name: Package
+      - name: Determine tag name
+        id: tag
         shell: bash
         run: |
-          mkdir -p nitro && mkdir -p nitro/config
-          cp config.json nitro/config/
-          cp build/nitro nitro/
-          zip -r nitro.zip nitro
+          BUILD_NUMBER="$(git rev-list --count HEAD)"
+          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
+          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
+            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
+          else
+            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
+            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
+          fi
 
-      - name: Upload binaries to release
+      - name: Pack artifacts
+        id: pack_artifacts
         if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
-        uses: svenstaro/upload-release-action@v2
+        run: |
+          7z a nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\*
+
+      - name: Upload artifacts
+        # if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
+        with:
+          path: |
+            nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip
+
+      - name: Copy and pack Cuda runtime
+        run: |
+          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
+          $dst='.\build\bin\cudart\'
+          robocopy "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
+          robocopy build_deps\_install\bin\zlib.dll $dst
+          robocopy build\bin\Release\llama.dll $dst
+          7z a cudart-nitro-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\*
+
+      - name: Upload Cuda runtime
+        # if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
         with:
-          repo_token: ${{ secrets.GITHUB_TOKEN }}
-          file: nitro.zip
-          asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-mac-amd64.zip.zip
-          tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
\ No newline at end of file
+          path: |
+            cudart-nitro-bin-win-cu${{ matrix.cuda }}-x64.zip
\ No newline at end of file

From a22e01514a579c7f9e42bd66d75470f25624bc34 Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Sun, 8 Oct 2023 19:01:26 +0700
Subject: [PATCH 2/9] fix(ci): Update windows-nvidia runners and git clone
 recursive

---
 .github/workflows/build.yml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index cdd28a198..c346a7a92 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -254,7 +254,7 @@ jobs:
         id: checkout
         uses: actions/checkout@v3
         with:
-          fetch-depth: 0
+          submodules: recursive
 
       - name: Download OpenCL SDK
         id: get_opencl
@@ -343,7 +343,7 @@ jobs:
             nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip
 
   windows-latest-cmake-cublas:
-    runs-on: windows-gpu
+    runs-on: windows-nvidia
 
     strategy:
       matrix:
@@ -355,7 +355,7 @@ jobs:
         id: checkout
         uses: actions/checkout@v3
         with:
-          fetch-depth: 0
+          submodules: recursive
 
       - uses: Jimver/cuda-toolkit@v0.2.11
         id: cuda-toolkit

From 17a5d89b97eeed881114517fe007063912619790 Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Sun, 8 Oct 2023 19:06:19 +0700
Subject: [PATCH 3/9] fix(ci-windows): Update cmake for preparation

---
 .github/workflows/build.yml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index c346a7a92..9506d0b7f 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -293,6 +293,7 @@ jobs:
       - name: Build
         id: cmake_build
         run: |
+          cmake -S ./nitro_deps -B ./build_deps/nitro_deps
           cmake --build ./build_deps/nitro_deps --config Release
           mkdir build
           cd build
@@ -367,6 +368,7 @@ jobs:
       - name: Build
         id: cmake_build
         run: |
+          cmake -S ./nitro_deps -B ./build_deps/nitro_deps
           cmake --build ./build_deps/nitro_deps --config Release
           mkdir build
           cd build

From 3770272731adec604e67c5ed9e87d47f65a4c498 Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Sun, 8 Oct 2023 19:29:29 +0700
Subject: [PATCH 4/9] fix(ci-windows): Update step name, remove cuda-toolkit
 installation, Add release job

---
 .github/workflows/build.yml | 85 +++++++++++++++++++++++++++++++------
 1 file changed, 71 insertions(+), 14 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 9506d0b7f..000c41e95 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -229,7 +229,7 @@ jobs:
   #         asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-mac-amd64.zip.zip
   #         tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
 
-  windows-latest-cmake:
+  windows-amd64-build:
     runs-on: windows-latest
 
     env:
@@ -240,12 +240,8 @@ jobs:
     strategy:
       matrix:
         include:
-          - build: 'avx2'
-            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON'
           - build: 'avx512'
             defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
-          - build: 'clblast'
-            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
           - build: 'openblas'
             defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
 
@@ -343,12 +339,12 @@ jobs:
           path: |
             nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip
 
-  windows-latest-cmake-cublas:
+  windows-amd64-cuda-build:
     runs-on: windows-nvidia
 
     strategy:
       matrix:
-        cuda: ['12.2.0', '11.7.1']
+        cuda: ['12.2.0']
         build: ['cublas']
 
     steps:
@@ -358,12 +354,12 @@ jobs:
         with:
           submodules: recursive
 
-      - uses: Jimver/cuda-toolkit@v0.2.11
-        id: cuda-toolkit
-        with:
-          cuda: ${{ matrix.cuda }}
-          method: 'network'
-          sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
+      # - uses: Jimver/cuda-toolkit@v0.2.11
+      #   id: cuda-toolkit
+      #   with:
+      #     cuda: ${{ matrix.cuda }}
+      #     method: 'network'
+      #     sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
 
       - name: Build
         id: cmake_build
@@ -415,4 +411,65 @@ jobs:
         uses: actions/upload-artifact@v3
         with:
           path: |
-            cudart-nitro-bin-win-cu${{ matrix.cuda }}-x64.zip
\ No newline at end of file
+            cudart-nitro-bin-win-cu${{ matrix.cuda }}-x64.zip
+
+  release:
+    runs-on: ubuntu-latest
+
+    needs:
+      - windows-amd64-build
+      - windows-amd64-cuda-build
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Determine tag name
+        id: tag
+        shell: bash
+        run: |
+          BUILD_NUMBER="$(git rev-list --count HEAD)"
+          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
+          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
+            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
+          else
+            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
+            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Download artifacts
+        id: download-artifact
+        uses: actions/download-artifact@v3
+
+      - name: Create release
+        id: create_release
+        uses: anzz1/action-create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ${{ steps.tag.outputs.name }}
+
+      - name: Upload release
+        id: upload_release
+        uses: actions/github-script@v3
+        with:
+          github-token: ${{secrets.GITHUB_TOKEN}}
+          script: |
+            const path = require('path');
+            const fs = require('fs');
+            const release_id = '${{ steps.create_release.outputs.id }}';
+            for (let file of await fs.readdirSync('./artifact')) {
+              if (path.extname(file) === '.zip') {
+                console.log('uploadReleaseAsset', file);
+                await github.repos.uploadReleaseAsset({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  release_id: release_id,
+                  name: file,
+                  data: await fs.readFileSync(`./artifact/${file}`)
+                });
+              }
+            }
\ No newline at end of file

From 0b08e1c394f8e2709bb0da3fb8f7c3d02d4a7152 Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Sun, 8 Oct 2023 19:50:47 +0700
Subject: [PATCH 5/9] fix(ci-windows): Use 1 value in windows matrix, package
 nitro windows GPU dll

---
 .github/workflows/build.yml | 185 +++++++++---------------------------
 1 file changed, 44 insertions(+), 141 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 000c41e95..6a3bdfb0b 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -226,11 +226,13 @@ jobs:
   #       with:
   #         repo_token: ${{ secrets.GITHUB_TOKEN }}
   #         file: nitro.zip
-  #         asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-mac-amd64.zip.zip
+  #         asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-mac-amd64.zip
   #         tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
 
   windows-amd64-build:
     runs-on: windows-latest
+    permissions:
+      contents: write
 
     env:
       OPENBLAS_VERSION: 0.3.23
@@ -240,39 +242,17 @@ jobs:
     strategy:
       matrix:
         include:
-          - build: 'avx512'
-            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
           - build: 'openblas'
             defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
 
     steps:
       - name: Clone
+  
         id: checkout
         uses: actions/checkout@v3
         with:
           submodules: recursive
 
-      - name: Download OpenCL SDK
-        id: get_opencl
-        if: ${{ matrix.build == 'clblast' }}
-        run: |
-          curl.exe -o $env:RUNNER_TEMP/opencl.zip -L "https://github.com/KhronosGroup/OpenCL-SDK/releases/download/v${env:OPENCL_VERSION}/OpenCL-SDK-v${env:OPENCL_VERSION}-Win-x64.zip"
-          mkdir $env:RUNNER_TEMP/opencl
-          tar.exe -xvf $env:RUNNER_TEMP/opencl.zip --strip-components=1 -C $env:RUNNER_TEMP/opencl
-
-      - name: Download CLBlast
-        id: get_clblast
-        if: ${{ matrix.build == 'clblast' }}
-        run: |
-          curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z"
-          curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE"
-          7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z
-          rename-item $env:RUNNER_TEMP/CLBlast-${env:CLBLAST_VERSION}-windows-x64 clblast
-          foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) {
-            $txt = Get-Content -Path $f -Raw
-            $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8
-          }
-
       - name: Download OpenBLAS
         id: get_openblas
         if: ${{ matrix.build == 'openblas' }}
@@ -296,51 +276,46 @@ jobs:
           cmake .. ${{ matrix.defines }}
           cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
 
-      - name: Add clblast.dll
-        id: add_clblast_dll
-        if: ${{ matrix.build == 'clblast' }}
-        run: |
-          cp $env:RUNNER_TEMP/clblast/lib/clblast.dll ./build/bin/Release
-          cp $env:RUNNER_TEMP/CLBlast.LICENSE.txt ./build/bin/Release/CLBlast-${env:CLBLAST_VERSION}.txt
-
       - name: Add libopenblas.dll
         id: add_libopenblas_dll
         if: ${{ matrix.build == 'openblas' }}
         run: |
-          cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/bin/Release/openblas.dll
-          cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/bin/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt
+          cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/Release/openblas.dll
+          cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt
 
-      - name: Determine tag name
-        id: tag
+      - name: Extract branch name
         shell: bash
-        run: |
-          BUILD_NUMBER="$(git rev-list --count HEAD)"
-          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
-          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
-            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
-          else
-            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
-            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
-          fi
+        id: extract_branch
+        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
+    
+      - name: Extract commit short SHA
+        id: extract_commit_id
+        run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
 
       - name: Pack artifacts
         id: pack_artifacts
         # if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
         run: |
-          Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt
+          $dst='.\build\Release'
           robocopy build_deps\_install\bin\zlib.dll $dst
           robocopy build\bin\Release\llama.dll $dst
-          7z a nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip .\build\bin\Release\*
+          mkdir -p .\build\Release\config
+          robocopy config.json .\build\Release\config
+          7z a nitro.zip .\build\Release\*
 
-      - name: Upload artifacts
+      - name: Upload binaries to release
         # if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
-        uses: actions/upload-artifact@v3
+        uses: svenstaro/upload-release-action@v2
         with:
-          path: |
-            nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-x64.zip
+          repo_token: ${{ secrets.GITHUB_TOKEN }}
+          file: nitro.zip
+          asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-win-amd64-${{ matrix.build }}.zip
+          tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
 
   windows-amd64-cuda-build:
     runs-on: windows-nvidia
+    permissions:
+      contents: write
 
     strategy:
       matrix:
@@ -371,105 +346,33 @@ jobs:
           cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
           cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
 
-      - name: Determine tag name
-        id: tag
+      - name: Extract branch name
         shell: bash
-        run: |
-          BUILD_NUMBER="$(git rev-list --count HEAD)"
-          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
-          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
-            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
-          else
-            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
-            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
-          fi
+        id: extract_branch
+        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
+    
+      - name: Extract commit short SHA
+        id: extract_commit_id
+        run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
+  
 
       - name: Pack artifacts
         id: pack_artifacts
         if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
         run: |
-          7z a nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip .\build\bin\Release\*
-
-      - name: Upload artifacts
-        # if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
-        uses: actions/upload-artifact@v3
-        with:
-          path: |
-            nitro-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip
-
-      - name: Copy and pack Cuda runtime
-        run: |
-          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
-          $dst='.\build\bin\cudart\'
-          robocopy "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
+          $dst='.\build\Release'
           robocopy build_deps\_install\bin\zlib.dll $dst
           robocopy build\bin\Release\llama.dll $dst
-          7z a cudart-nitro-bin-win-cu${{ matrix.cuda }}-x64.zip $dst\*
+          robocopy "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
+          mkdir -p .\build\Release\config
+          robocopy config.json .\build\Release\config
+          7z a nitro.zip .\build\Release\*
 
-      - name: Upload Cuda runtime
+      - name: Upload binaries to release
         # if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
-        uses: actions/upload-artifact@v3
-        with:
-          path: |
-            cudart-nitro-bin-win-cu${{ matrix.cuda }}-x64.zip
-
-  release:
-    runs-on: ubuntu-latest
-
-    needs:
-      - windows-amd64-build
-      - windows-amd64-cuda-build
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-
-      - name: Determine tag name
-        id: tag
-        shell: bash
-        run: |
-          BUILD_NUMBER="$(git rev-list --count HEAD)"
-          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
-          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
-            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
-          else
-            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
-            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Download artifacts
-        id: download-artifact
-        uses: actions/download-artifact@v3
-
-      - name: Create release
-        id: create_release
-        uses: anzz1/action-create-release@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          tag_name: ${{ steps.tag.outputs.name }}
-
-      - name: Upload release
-        id: upload_release
-        uses: actions/github-script@v3
+        uses: svenstaro/upload-release-action@v2
         with:
-          github-token: ${{secrets.GITHUB_TOKEN}}
-          script: |
-            const path = require('path');
-            const fs = require('fs');
-            const release_id = '${{ steps.create_release.outputs.id }}';
-            for (let file of await fs.readdirSync('./artifact')) {
-              if (path.extname(file) === '.zip') {
-                console.log('uploadReleaseAsset', file);
-                await github.repos.uploadReleaseAsset({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  release_id: release_id,
-                  name: file,
-                  data: await fs.readFileSync(`./artifact/${file}`)
-                });
-              }
-            }
\ No newline at end of file
+          repo_token: ${{ secrets.GITHUB_TOKEN }}
+          file: nitro.zip
+          asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-win-amd64-${{ matrix.build }}-cu${{ matrix.cuda }}.zip
+          tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}

From 2882bb41ee53ec6db1594f2649e1d23693485603 Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Sun, 8 Oct 2023 19:56:43 +0700
Subject: [PATCH 6/9] fix(ci-windows): Update cmd as shell

---
 .github/workflows/build.yml | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 6a3bdfb0b..4ab9b021d 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -268,6 +268,7 @@ jobs:
 
       - name: Build
         id: cmake_build
+        shell: cmd
         run: |
           cmake -S ./nitro_deps -B ./build_deps/nitro_deps
           cmake --build ./build_deps/nitro_deps --config Release
@@ -284,11 +285,12 @@ jobs:
           cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt
 
       - name: Extract branch name
-        shell: bash
+        shell: cmd
         id: extract_branch
         run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
     
       - name: Extract commit short SHA
+        shell: cmd
         id: extract_commit_id
         run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
 
@@ -338,6 +340,7 @@ jobs:
 
       - name: Build
         id: cmake_build
+        shell: cmd
         run: |
           cmake -S ./nitro_deps -B ./build_deps/nitro_deps
           cmake --build ./build_deps/nitro_deps --config Release
@@ -347,11 +350,12 @@ jobs:
           cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
 
       - name: Extract branch name
-        shell: bash
+        shell: cmd
         id: extract_branch
         run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
     
       - name: Extract commit short SHA
+        shell: cmd
         id: extract_commit_id
         run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
   

From 3da740aba5cf3768872abe9ea6cb920bc8ad11cb Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Sun, 8 Oct 2023 20:10:45 +0700
Subject: [PATCH 7/9] fix(ci-windows): Fix cmake build -j nproc

---
 .github/workflows/build.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 4ab9b021d..88e6867b0 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -275,7 +275,7 @@ jobs:
           mkdir build
           cd build
           cmake .. ${{ matrix.defines }}
-          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
+          cmake --build . --config Release -j $(nproc)
 
       - name: Add libopenblas.dll
         id: add_libopenblas_dll
@@ -347,7 +347,7 @@ jobs:
           mkdir build
           cd build
           cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
-          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
+          cmake --build . --config Release -j $(nproc)
 
       - name: Extract branch name
         shell: cmd

From 3fbfab0673ddb3efdc972dac270da8712da2caf9 Mon Sep 17 00:00:00 2001
From: vuonghoainam <vuonghoainam.work@gmail.com>
Date: Sun, 8 Oct 2023 21:01:38 +0700
Subject: [PATCH 8/9] fix(ci-windows): Update nproc

---
 .github/workflows/build.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 88e6867b0..1f299c5b0 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -275,7 +275,7 @@ jobs:
           mkdir build
           cd build
           cmake .. ${{ matrix.defines }}
-          cmake --build . --config Release -j $(nproc)
+          cmake --build . --config Release -j 4
 
       - name: Add libopenblas.dll
         id: add_libopenblas_dll
@@ -347,7 +347,7 @@ jobs:
           mkdir build
           cd build
           cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
-          cmake --build . --config Release -j $(nproc)
+          cmake --build . --config Release -j 4
 
       - name: Extract branch name
         shell: cmd

From aafcb82077bfb657130935ea0407d971b26f6fb3 Mon Sep 17 00:00:00 2001
From: Hien To <tominhhien97@gmail.com>
Date: Fri, 13 Oct 2023 13:50:16 +0700
Subject: [PATCH 9/9] Refactor CICD windows nitro

---
 .github/workflows/build.yml | 133 +++++++++++++-----------------------
 1 file changed, 49 insertions(+), 84 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index b65f000c0..31dc9614e 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -45,29 +45,15 @@ jobs:
     if: always() && (needs.create-draft-release.result == 'success' || needs.create-draft-release.result == 'skipped')
     permissions:
       contents: write
-
-    env:
-      OPENBLAS_VERSION: 0.3.23
-      OPENCL_VERSION: 2023.04.17
-      CLBLAST_VERSION: 1.6.0
-
-    strategy:
-      matrix:
-        include:
-          - build: 'openblas'
-            defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
-
     steps:
       - name: Clone
-  
         id: checkout
         uses: actions/checkout@v3
         with:
           submodules: recursive
 
-      - name: Download OpenBLAS
-        id: get_openblas
-        if: ${{ matrix.build == 'openblas' }}
+      - name: Dependencies
+        id: depends
         run: |
           sudo apt-get update
           sudo apt-get install build-essential gcc-8
@@ -167,7 +153,6 @@ jobs:
 
       - name: Build
         id: cmake_build
-        shell: cmd
         run: |
           ./install_deps.sh
           mkdir build && cd build
@@ -225,12 +210,10 @@ jobs:
       - name: Package
         shell: bash
         run: |
-          $dst='.\build\Release'
-          robocopy build_deps\_install\bin\zlib.dll $dst
-          robocopy build\bin\Release\llama.dll $dst
-          mkdir -p .\build\Release\config
-          robocopy config.json .\build\Release\config
-          7z a nitro.zip .\build\Release\*
+          mkdir -p nitro && mkdir -p nitro/config
+          cp config.json nitro/config/
+          cp build/nitro nitro/
+          zip -r nitro.zip nitro
 
       - uses: actions/upload-release-asset@v1.0.1
         if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
@@ -244,6 +227,8 @@ jobs:
 
   windows-amd64-build:
     runs-on: windows-latest
+    needs: create-draft-release
+    if: always() && (needs.create-draft-release.result == 'success' || needs.create-draft-release.result == 'skipped')
     permissions:
       contents: write
 
@@ -255,7 +240,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - build: 'openblas'
+          - build: 'normal'
             defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
 
     steps:
@@ -266,18 +251,17 @@ jobs:
         with:
           submodules: recursive
 
-      - name: Download OpenBLAS
-        id: get_openblas
-        if: ${{ matrix.build == 'openblas' }}
-        run: |
-          curl.exe -o $env:RUNNER_TEMP/openblas.zip -L "https://github.com/xianyi/OpenBLAS/releases/download/v${env:OPENBLAS_VERSION}/OpenBLAS-${env:OPENBLAS_VERSION}-x64.zip"
-          curl.exe -o $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt -L "https://github.com/xianyi/OpenBLAS/raw/v${env:OPENBLAS_VERSION}/LICENSE"
-          mkdir $env:RUNNER_TEMP/openblas
-          tar.exe -xvf $env:RUNNER_TEMP/openblas.zip -C $env:RUNNER_TEMP/openblas
-          $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath)
-          $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim()))
-          $lib =  $(join-path $msvc 'bin\Hostx64\x64\lib.exe')
-          & $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll
+      - name: Setup VSWhere.exe
+        uses: warrenbuckley/Setup-VSWhere@v1
+        with:
+          version: latest
+          silent: true
+        env:
+          ACTIONS_ALLOW_UNSECURE_COMMANDS: true
+  
+
+      - name: actions-setup-cmake
+        uses: jwlawson/actions-setup-cmake@v1.14.1
 
       - name: Build
         id: cmake_build
@@ -287,26 +271,9 @@ jobs:
           cmake --build ./build_deps/nitro_deps --config Release
           mkdir build
           cd build
-          cmake .. ${{ matrix.defines }}
+          cmake ..
           cmake --build . --config Release -j 4
 
-      - name: Add libopenblas.dll
-        id: add_libopenblas_dll
-        if: ${{ matrix.build == 'openblas' }}
-        run: |
-          cp $env:RUNNER_TEMP/openblas/bin/libopenblas.dll ./build/Release/openblas.dll
-          cp $env:RUNNER_TEMP/OpenBLAS.LICENSE.txt ./build/Release/OpenBLAS-${env:OPENBLAS_VERSION}.txt
-
-      - name: Extract branch name
-        shell: cmd
-        id: extract_branch
-        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
-    
-      - name: Extract commit short SHA
-        shell: cmd
-        id: extract_commit_id
-        run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
-
       - name: Pack artifacts
         id: pack_artifacts
         run: |
@@ -317,16 +284,20 @@ jobs:
           robocopy config.json .\build\Release\config
           7z a nitro.zip .\build\Release\*
 
-      - name: Upload binaries to release
-        uses: svenstaro/upload-release-action@v2
+      - uses: actions/upload-release-asset@v1.0.1
+        if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
-          repo_token: ${{ secrets.GITHUB_TOKEN }}
-          file: nitro.zip
-          asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-win-amd64-${{ matrix.build }}.zip
-          tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}
+          upload_url: ${{ needs.create-draft-release.outputs.upload_url }}
+          asset_path: ./nitro.zip
+          asset_name: nitro-${{ needs.create-draft-release.outputs.version }}-win-amd64-${{ matrix.build }}.zip
+          asset_content_type: application/zip
 
   windows-amd64-cuda-build:
     runs-on: windows-nvidia
+    needs: create-draft-release
+    if: always() && (needs.create-draft-release.result == 'success' || needs.create-draft-release.result == 'skipped')
     permissions:
       contents: write
 
@@ -342,12 +313,13 @@ jobs:
         with:
           submodules: recursive
 
-      # - uses: Jimver/cuda-toolkit@v0.2.11
-      #   id: cuda-toolkit
-      #   with:
-      #     cuda: ${{ matrix.cuda }}
-      #     method: 'network'
-      #     sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
+      - name: Setup VSWhere.exe
+        uses: warrenbuckley/Setup-VSWhere@v1
+        with:
+          version: latest
+          silent: true
+        env:
+          ACTIONS_ALLOW_UNSECURE_COMMANDS: true
 
       - name: Build
         id: cmake_build
@@ -360,35 +332,28 @@ jobs:
           cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
           cmake --build . --config Release -j 4
 
-      - name: Extract branch name
-        shell: cmd
-        id: extract_branch
-        run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"   
-    
-      - name: Extract commit short SHA
-        shell: cmd
-        id: extract_commit_id
-        run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
-  
-
       - name: Pack artifacts
         id: pack_artifacts
+        shell: cmd
         run: |
+          set PATH=%PATH%;C:\Program Files\7-Zip\
+          echo %PATH%
           $dst='.\build\Release'
           robocopy build_deps\_install\bin\zlib.dll $dst
           robocopy build\bin\Release\llama.dll $dst
-          robocopy "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
           mkdir -p .\build\Release\config
           robocopy config.json .\build\Release\config
           7z a nitro.zip .\build\Release\*
 
-      - name: Upload binaries to release
-        uses: svenstaro/upload-release-action@v2
+      - uses: actions/upload-release-asset@v1.0.1
+        if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
-          repo_token: ${{ secrets.GITHUB_TOKEN }}
-          file: nitro.zip
-          asset_name: nitro-${{ steps.extract_commit_id.outputs.sha_short }}-win-amd64-${{ matrix.build }}-cu${{ matrix.cuda }}.zip
-          tag: ${{ steps.extract_branch.outputs.branch }}-${{ steps.extract_commit_id.outputs.sha_short }}          
+          upload_url: ${{ needs.create-draft-release.outputs.upload_url }}
+          asset_path: ./nitro.zip
+          asset_name: nitro-${{ needs.create-draft-release.outputs.version }}-win-amd64-${{ matrix.build }}-cu${{ matrix.cuda }}.zip
+          asset_content_type: application/zip        
           
   update_release_draft:
     needs: [ubuntu-amd64-build, ubuntu-amd64-cuda-build, macOS-M-build, macOS-Intel-build, windows-amd64-build, windows-amd64-cuda-build]