diff --git a/.github/workflows/release-tamagotchi.yml b/.github/workflows/release-tamagotchi.yml index cbb5b8f25..69e05c164 100644 --- a/.github/workflows/release-tamagotchi.yml +++ b/.github/workflows/release-tamagotchi.yml @@ -77,11 +77,11 @@ jobs: sudo apt-get update sudo apt-get install -y libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf - # - name: Install CUDA Toolkit (Linux and Windows Only) - # uses: Jimver/cuda-toolkit@v0.2.24 - # if: matrix.os == 'ubuntu-latest' || matrix.os == 'ubuntu-24.04-arm' || matrix.os == 'windows-latest' - # with: - # cuda: 12.5.0 + - name: Install CUDA Toolkit (Linux and Windows Only) + uses: Jimver/cuda-toolkit@v0.2.24 + if: matrix.os == 'ubuntu-latest' || matrix.os == 'ubuntu-24.04-arm' || matrix.os == 'windows-latest' + with: + cuda: 12.5.0 - name: Install dependencies run: pnpm install --frozen-lockfile @@ -95,8 +95,43 @@ jobs: - name: Build Application (Linux and Windows Only) if: matrix.os == 'ubuntu-latest' || matrix.os == 'ubuntu-24.04-arm' || matrix.os == 'windows-latest' - # run: cd apps/stage-tamagotchi && pnpm tauri build --target ${{ matrix.target }} --features cuda - run: cd apps/stage-tamagotchi && pnpm tauri build --target ${{ matrix.target }} + run: cd apps/stage-tamagotchi && pnpm tauri build --target ${{ matrix.target }} --features cuda + env: + # Call to `nvcc` (which part of the CUDA Toolkit) doesn't require a physical GPU, yet bindgen_cuda requires `nvidia-smi` + # to be available in order to determine the compute capability of the GPU.[^1] + # + # And bindgen_cuda is what candle depends on, to bypass the Compute compatibility here, + # we need to explicitly setting CUDA_COMPUTE_CAP as one of the environment varaible in order to + # build without any actual physical GPUs inside of the GitHub Actions runner.[^2] + # + # About how bindgen_cuda depends on nvidia-smi, check the actual source code here: + # https://github.com/Narsil/bindgen_cuda/blob/a6b0c891be8ebefb55600d46d8a77a358adc3913/src/lib.rs#L477-L500 + # + # Similar information were seen from TEI (text-embedding-inference) documentations + # https://huggingface.co/docs/text-embeddings-inference/en/custom_container + # + # To understand what compute capability is required, visit [CUDA GPU Compute Capability](https://developer.nvidia.com/cuda-gpus) + # + # In short: + # | Compute Capability | GeForce / RTX | + # |---------------------|----------------| + # | 7.5 | GeForce GTX 1650 Ti, NVIDIA TITAN RTX, GeForce RTX 2000 series... | + # | 8.6 | RTX A series, GeForce RTX 3000 series | + # | 8.9 | GeForce RTX 4000 series, RTX A Ada series | + # | 9.0 | GeForce RTX 5000 series, RTX Pro Blackwell series | + # + # Also, the meaning of how the different ranges of numeric values will impact on which compilers, dependencies, to be used, + # TEI (text-embedding-inference) got a Dockerfile specified that well + # https://github.com/huggingface/text-embeddings-inference/blob/6e900afba71821fdf250e380d7da1f5a6e5e7e27/Dockerfile-cuda#L50-L63 + # + # Thanks + # - https://github.com/Narsil/bindgen_cuda/issues/4 + # - https://github.com/Narsil/bindgen_cuda/issues/8 + # - https://github.com/huggingface/candle/issues/1516#issuecomment-1875440701 + # + # [^1]: compilation - Can I compile a cuda program without having a cuda device - Stack Overflow https://stackoverflow.com/a/20196425 + # [^2]: https://huggingface.github.io/candle/guide/installation.html + CUDA_COMPUTE_CAP: '75' - name: Rename Artifacts (Nightly) if: ${{ github.event_name == 'schedule' }}