diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index f6a2dd6da..b788b3d75 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -69,6 +69,149 @@ jobs:
           cd build
           ctest --verbose --timeout 900
 
+  ubuntu-focal-cmake:
+    runs-on: ubuntu-20.04
+
+    strategy:
+      matrix:
+        include:
+          - build: 'avx2'
+            defines: ''
+          - build: 'avx'
+            defines: '-DLLAMA_AVX2=OFF'
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v1
+
+      - name: Dependencies
+        id: depends
+        run: |
+          sudo apt-get update
+          sudo apt-get install build-essential
+
+      - name: Build
+        id: cmake_build
+        run: |
+          mkdir build
+          cd build
+          cmake .. ${{ matrix.defines }} -DCMAKE_BUILD_RPATH_USE_ORIGIN=ON -DBUILD_SHARED_LIBS=ON
+          cmake --build . --config Release
+
+      - name: Test
+        id: cmake_test
+        run: |
+          cd build
+          ctest --verbose
+
+      - name: Get commit hash
+        id: commit
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: pr-mpt/actions-commit-hash@v2
+
+      - name: Pack artifacts
+        id: pack_artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        run: |
+          7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-ubuntu20.04-${{ matrix.build }}-x64.zip ./build/bin/*
+
+      - name: Upload artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
+        with:
+          path: |
+            llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-ubuntu20.04-${{ matrix.build }}-x64.zip
+
+  ubuntu-focal-cmake-cublas:
+    runs-on: ubuntu-20.04
+
+    strategy:
+      matrix:
+        cuda: ['12.1.0', '11.7.1']
+        build: ['cublas']
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v1
+
+      - name: Dependencies
+        id: depends
+        run: |
+          sudo apt-get update
+          sudo apt-get install build-essential
+
+      - uses: Jimver/cuda-toolkit@v0.2.11
+        id: cuda-toolkit
+        with:
+          cuda: ${{ matrix.cuda }}
+          method: 'network'
+          linux-local-args: '["--toolkit"]'
+          #TODO(green-sky): the action prefixes "cublas-dev" with "cuda-" instead of "lib"
+          #sub-packages: '["nvcc", "cudart", "cublas-dev"]'
+          sub-packages: '["nvcc", "cudart"]'
+          non-cuda-sub-packages: '["libcublas", "libcublas-dev"]'
+
+      - name: Build
+        id: cmake_build
+        run: |
+          mkdir build
+          cd build
+          cmake .. -DLLAMA_CUBLAS=ON -DCMAKE_BUILD_RPATH_USE_ORIGIN=ON -DBUILD_SHARED_LIBS=ON
+          cmake --build . --config Release
+
+      - name: Get commit hash
+        id: commit
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: pr-mpt/actions-commit-hash@v2
+
+      - name: Pack artifacts
+        id: pack_artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        run: |
+          7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-ubuntu20.04-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip ./build/bin/*
+
+      - name: Upload artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
+        with:
+          path: |
+            llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-ubuntu20.04-${{ matrix.build }}-cu${{ matrix.cuda }}-x64.zip
+
+      - name: Copy and pack Cuda runtime
+        if: ${{ matrix.cuda == '12.1.0' }}
+        # TODO(green-sky): paths are cuda 12 specific
+        run: |
+          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
+          mkdir './build/bin/cudart/'
+          ls "${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
+          ls "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/bin"
+          ls "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/lib64"
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/lib64/libcudart.so.12" './build/bin/cudart/'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/lib64/libcublas.so.12" './build/bin/cudart/'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/lib64/libcublasLt.so.12" './build/bin/cudart/'
+          7z a cudart-llama-bin-ubuntu20.04-cu${{ matrix.cuda }}-x64.zip ./build/bin/cudart/*
+
+      - name: Copy and pack Cuda runtime
+        if: ${{ matrix.cuda == '11.7.1' }}
+        # TODO(green-sky): paths are cuda 11 specific
+        run: |
+          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
+          mkdir './build/bin/cudart/'
+          ls "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/lib64"
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/lib64/libcudart.so.11.0" './build/bin/cudart/'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/lib64/libcublas.so.11" './build/bin/cudart/'
+          cp "${{steps.cuda-toolkit.outputs.CUDA_PATH}}/lib64/libcublasLt.so.11" './build/bin/cudart/'
+          7z a cudart-llama-bin-ubuntu20.04-cu${{ matrix.cuda }}-x64.zip ./build/bin/cudart/*
+
+      - name: Upload Cuda runtime
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-artifact@v3
+        with:
+          path: |
+            cudart-llama-bin-ubuntu20.04-cu${{ matrix.cuda }}-x64.zip
+
   ubuntu-latest-cmake-sanitizer:
     runs-on: ubuntu-latest
 
@@ -358,6 +501,8 @@ jobs:
     needs:
       - ubuntu-focal-make
       - ubuntu-latest-cmake
+      - ubuntu-focal-cmake
+      - ubuntu-focal-cmake-cublas
       - macOS-latest-make
       - macOS-latest-cmake
       - windows-latest-cmake
diff --git a/CMakeLists.txt b/CMakeLists.txt
index a2404548f..39b5f3c50 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -8,6 +8,7 @@ if (NOT XCODE AND NOT MSVC AND NOT CMAKE_BUILD_TYPE)
     set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS "Debug" "Release" "MinSizeRel" "RelWithDebInfo")
 endif()
 
+set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
 set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
 
 if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR)