From 02d5316af5f9cef149ec20eebcba99cd6395b6b3 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Thu, 4 Jun 2026 09:35:58 +0300 Subject: [PATCH] ci : refactor + optimize (#3847) * ci : add ccache clear action * ci : split self-hosted GPU jobs into build-self-hosted.yml Extract self-hosted runner jobs from build.yml into a dedicated build-self-hosted.yml following the llama.cpp pattern: - gpu-cuda (NVIDIA Linux) - gpu-vulkan-nvidia-cm (NVIDIA Linux) - gpu-vulkan-nvidia-cm2 (NVIDIA Linux + COOPMAT2) - gpu-metal (macOS ARM64) - gpu-vulkan (macOS ARM64) GitHub-hosted CPU jobs remain in build.yml. Assisted-by: llama.cpp:local pi * ci : split release jobs into release.yml Extract release-related jobs from build.yml into a dedicated release.yml following the llama.cpp pattern: - determine-tag - windows (Win32/x64, SDL2) - windows-blas (Win32/x64, OpenBLAS) - windows-cublas (x64, CUDA 11.8/12.4) - ios-xcode-build - bindings-java (depends on windows) - release (artifact aggregation + GitHub release) CoreML job stays in build.yml with its own local tag calculation. Assisted-by: llama.cpp:local pi * ci : remove bindings-java job from release.yml Assisted-by: llama.cpp:local pi * cont : add manual trigger for build.yml * cont : remove obsolete ifs * ci : extract sanitizer job to bild-sanitize.yml * ci : extract linux jobs into build-linux.yml * ci : extract macos jobs to build-macos.yml * ci : extract gcc jobs to build-gcc.yml * ci : extract clang jobs to build-clang.yml * ci : extract sycl jobs to build-sycl.yml * ci : extract windows jobs to build-windows.yml * ci : extract emscripten job to build-wasm.yml * ci : extract android jobs into build-android.yml * ci : extract quantize job to quantize.yml * ci : extract coreml job into coreml.yml * ci : extract vad job to vad.yml * ci : extract cpu jobs to build-cpu.yml * ci : make naming of yml files consistent * ci : add --fail to curl download and propagate This commit adds the --fail option to the model download scripts so that if the model download returns a server error this is picked up. This is then detected in run.sh and a error message is displayed and the script stops and returns an error. The motivation for this is that currently it is possible for the model download to fail but this script proceeds and instead of a model file the contents will be an html page probably with the error. This will then cause the model to not be able to load due to a missing magic number. I'm not sure we can do much about the downloading failing, perhaps a retry but at least this will give a clearer error message. Refs: https://github.com/danbev/whisper.cpp/actions/runs/26866349389/job/79230794512 * ci : enable command traces to see download command in use * ci : add retry functionality to download model script This commit adds curl retry options to the model download script. The motivation is that currently when CI jobs run huggingface rate limit the requests and return: ```console curl: (22) The requested URL returned error: 429 ``` This is an attempt to work around this and if it does not work then we can an authorization token. * ci : extract freebsd job to build-freebsd.yml This job has been commented out as it has been flaky in the past. I'll monitor this and if it continues to be unreliable we can disable it in the github actions GUI instead of commenting it out like we did before. * ci : add ccache to jobs (non-docker builds) The ccache will only be saved on pushed to master. * ci : bump ccache-action version to v1.2.21 The motivation for this is that the save parameter does not seem to work with the current version. * ci : add ccache to docker jobs in build-linux.yml * ci : add debug statements to linux docker build * ci : set CCACHE_DIR for build-linux.yml * ci : add ccache to the remaining docker jobs * ci : remove build-linux.yml This commit remove build-linux.yml as the same jobs are also run by build-gcc.yml, with the exception that build-gcc.yml also run ctest). So keeping build-gcc.yml and removing the redundant build-linux.yml. * ci : add linux build artifacts to release * ci : revert to hendrikmuhs/ccache-action for win job This is currently causing the following failure: ```console sccache C:\PROGRA~1\NVIDIA~1\CUDA\v\bin\nvcc.exe -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_CRT_SECURE_NO_WARNINGS -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS -DCMAKE_INTDIR=\"Release\" -ID:\a\whisper.cpp\whisper.cpp\ggml\src\ggml-cuda\.. -ID:\a\whisper.cpp\whisper.cpp\ggml\src\..\include -isystem "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v\include" -Xcompiler="-MD -O2 -Ob2" -DNDEBUG -std=c++17 -arch=native -use_fast_math -extended-lambda -Xcompiler /Zc:preprocessor -MD -MT ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\Release\allreduce.cu.obj -MF ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\Release\allreduce.cu.obj.d -x cu -c D:\a\whisper.cpp\whisper.cpp\ggml\src\ggml-cuda\allreduce.cu -o ggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\Release\allreduce.cu.obj -Xcompiler=-Fdggml\src\ggml-cuda\CMakeFiles\ggml-cuda.dir\Release\,-FS sccache: encountered fatal error sccache: error: Could not parse shell line sccache: caused by: Could not parse shell line ``` Refs: https://github.com/danbev/whisper.cpp/actions/runs/26883673904/job/79290017353 * ci : make static linux artifacts * ci : make linux release artifact names consistent This commit removes the tag form the linux release artifacts to be consistent with the existing artifacts. If we want to include the tag then we can do that in a follow-up PR. * ci : fix linux zip files to have a directory * ci : add HF_TOKEN secret for HF download authorization This is to avoid the HR rate limiting when downloading model. --------- Co-authored-by: Daniel Bevenius --- .github/actions/ccache-clear/action.yml | 22 + .github/workflows/build-android.yml | 80 ++ .github/workflows/build-clang.yml | 121 ++ .github/workflows/build-coreml.yml | 65 + .github/workflows/build-cpu.yml | 173 +++ .github/workflows/build-freebsd.yml | 47 + .github/workflows/build-gcc.yml | 166 +++ .github/workflows/build-macos.yml | 72 ++ .github/workflows/build-quantize.yml | 41 + .github/workflows/build-sanitize.yml | 82 ++ .github/workflows/build-self-hosted.yml | 116 ++ .github/workflows/build-sycl.yml | 132 ++ .github/workflows/build-vad.yml | 43 + .github/workflows/build-wasm.yml | 51 + .github/workflows/build-windows.yml | 76 ++ .github/workflows/build.yml | 1573 ----------------------- .github/workflows/examples.yml | 2 + .github/workflows/release.yml | 649 ++++++++++ ci/run.sh | 7 + models/download-ggml-model.sh | 8 +- 20 files changed, 1952 insertions(+), 1574 deletions(-) create mode 100644 .github/actions/ccache-clear/action.yml create mode 100644 .github/workflows/build-android.yml create mode 100644 .github/workflows/build-clang.yml create mode 100644 .github/workflows/build-coreml.yml create mode 100644 .github/workflows/build-cpu.yml create mode 100644 .github/workflows/build-freebsd.yml create mode 100644 .github/workflows/build-gcc.yml create mode 100644 .github/workflows/build-macos.yml create mode 100644 .github/workflows/build-quantize.yml create mode 100644 .github/workflows/build-sanitize.yml create mode 100644 .github/workflows/build-self-hosted.yml create mode 100644 .github/workflows/build-sycl.yml create mode 100644 .github/workflows/build-vad.yml create mode 100644 .github/workflows/build-wasm.yml create mode 100644 .github/workflows/build-windows.yml delete mode 100644 .github/workflows/build.yml create mode 100644 .github/workflows/release.yml diff --git a/.github/actions/ccache-clear/action.yml b/.github/actions/ccache-clear/action.yml new file mode 100644 index 000000000..d38587efa --- /dev/null +++ b/.github/actions/ccache-clear/action.yml @@ -0,0 +1,22 @@ +name: "ccache-clear" +description: "Delete all GitHub Actions caches matching a key prefix" +inputs: + key: + description: "Cache key prefix to match and delete" + required: true + +runs: + using: "composite" + steps: + - name: Clear caches + shell: bash + run: | + CACHES=$(gh cache list --key "ccache-${{ inputs.key }}" --json id,key --jq '.[] | "\(.id) \(.key)"' 2>/dev/null) + if [ -z "$CACHES" ]; then + echo "No caches found with key prefix: ${{ inputs.key }}" + exit 0 + fi + while read -r id key; do + echo "Deleting cache: $id ($key)" + gh cache delete "$id" + done <<< "$CACHES" diff --git a/.github/workflows/build-android.yml b/.github/workflows/build-android.yml new file mode 100644 index 000000000..d9af18101 --- /dev/null +++ b/.github/workflows/build-android.yml @@ -0,0 +1,80 @@ +name: CI (android) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-android.yml', + '**/CMakeLists.txt', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.java'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + android: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + uses: actions/checkout@v6 + with: + path: whisper + + - name: Install Java + uses: actions/setup-java@v5 + with: + distribution: zulu + java-version: 21 + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + + - name: Build + run: | + cd whisper/examples/whisper.android + ./gradlew assembleRelease --no-daemon + + - name: Build with external ggml + run: | + export PATH_TO_GGML=$PWD/ggml + cd whisper/examples/whisper.android + ./gradlew assembleRelease --no-daemon + + android_java: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: set up JDK 11 + uses: actions/setup-java@v5 + with: + java-version: '11' + distribution: 'temurin' + cache: gradle + + - name: Setup Android SDK + uses: android-actions/setup-android@v3 + with: + cmdline-tools-version: 9.0 + + - name: Build + run: | + cd examples/whisper.android.java + chmod +x ./gradlew + ./gradlew assembleRelease diff --git a/.github/workflows/build-clang.yml b/.github/workflows/build-clang.yml new file mode 100644 index 000000000..c7a36884f --- /dev/null +++ b/.github/workflows/build-clang.yml @@ -0,0 +1,121 @@ +name: CI (clang) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-clang.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.in', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh', + '**/*.cl'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +env: + ubuntu_image: "ubuntu:22.04" + +jobs: + ubuntu-22-clang: + runs-on: ubuntu-22.04 + + strategy: + fail-fast: false + matrix: + build: [Debug, Release] + #arch: [linux/amd64, linux/arm64, linux/arm/v7, linux/ppc64le] + # TODO: arm/v7 disabled due to clang bug + # https://github.com/ggerganov/whisper.cpp/actions/runs/9657764109/job/26637633042?pr=2256#step:4:1990 + arch: [linux/amd64, linux/ppc64le] + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Set CCACHE_DIR + run: echo "CCACHE_DIR=${{ runner.temp }}/ccache" >> $GITHUB_ENV + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: clang-${{ matrix.arch }}-${{ matrix.build }} + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Set up QEMU + uses: docker/setup-qemu-action@v3 + + - name: Build ${{ matrix.arch }} + run: | + docker run --platform ${{ matrix.arch }} --rm \ + -v ${{ github.workspace }}:/workspace \ + -v ${CCACHE_DIR}:${CCACHE_DIR} \ + -e CCACHE_DIR=${CCACHE_DIR} \ + -w /workspace ${{ env.ubuntu_image }} /bin/sh -c ' + set -e + export DEBIAN_FRONTEND=noninteractive + sed -i "s|archive.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list + sed -i "s|security.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list + + apt update + apt install -y clang build-essential cmake libsdl2-dev git ccache + cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DCMAKE_CXX_COMPILER=clang++ \ + -DCMAKE_C_COMPILER=clang \ + -DCMAKE_C_COMPILER_LAUNCHER=ccache \ + -DCMAKE_CXX_COMPILER_LAUNCHER=ccache + make + ctest -L gh --output-on-failure' + + ubuntu-22-clang-arm64: + runs-on: ubuntu-22.04-arm + + strategy: + fail-fast: false + matrix: + build: [Debug, Release] + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: clang-arm64-${{ matrix.build }} + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Install dependencies + run: | + sudo apt-get update + sudo apt-get install -y clang build-essential cmake libsdl2-dev git + + - name: Build and Test + run: | + cmake . -DWHISPER_SDL2=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DCMAKE_CXX_COMPILER=clang++ \ + -DCMAKE_C_COMPILER=clang \ + -DGGML_NATIVE=OFF \ + -DGGML_CPU_ARM_ARCH=armv8-a + make + ctest -L gh --output-on-failure diff --git a/.github/workflows/build-coreml.yml b/.github/workflows/build-coreml.yml new file mode 100644 index 000000000..d383d9ae0 --- /dev/null +++ b/.github/workflows/build-coreml.yml @@ -0,0 +1,65 @@ +name: CI (coreml) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + tags: + - 'v*' + paths: ['.github/workflows/build-coreml.yml', + '**/CMakeLists.txt', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.swift', + '**/*.m', + '**/*.mm', + '**/*.metal'] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + +jobs: + coreml-base-en: + runs-on: macos-latest + + steps: + - name: Checkout with full history + uses: actions/checkout@v6 + with: + fetch-depth: 0 + + - name: Set environment variables + id: set_vars + run: | + BUILD_NUMBER=$(git rev-list --count HEAD) + SHORT_HASH=$(git rev-parse --short=7 HEAD) + if [[ "${{ github.ref_type }}" == "tag" ]]; then + TAG_NAME="${{ github.ref_name }}" + elif [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + TAG_NAME="b${BUILD_NUMBER}" + else + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + TAG_NAME="${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" + fi + echo "MODEL_NAME=base.en" >> $GITHUB_ENV + echo "GEN_MODEL_NAME=whisper-${TAG_NAME}-ggml-base.en-encoder.mlmodelc" >> $GITHUB_ENV + + - name: Download model + env: + HF_TOKEN: ${{ secrets.HF_TOKEN }} + run: | + ./models/download-ggml-model.sh ${{ env.MODEL_NAME }} + + - name: Generate CoreML model + run: | + python3.11 -m venv venv + source venv/bin/activate + pip install ane_transformers openai-whisper coremltools + ./models/generate-coreml-model.sh ${{ env.MODEL_NAME }} diff --git a/.github/workflows/build-cpu.yml b/.github/workflows/build-cpu.yml new file mode 100644 index 000000000..9c8e0586f --- /dev/null +++ b/.github/workflows/build-cpu.yml @@ -0,0 +1,173 @@ +name: CI (cpu) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-cpu.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.in', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh', + '**/*.cl'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +# TODO: simplify the following jobs using a matrix +jobs: + ggml-ci-x64-cpu-low-perf: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ggml-ci-x64-cpu-low-perf + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Test + id: ggml-ci + env: + HF_TOKEN: ${{ secrets.HF_TOKEN }} + run: | + LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt + + ggml-ci-arm64-cpu-low-perf: + runs-on: ubuntu-22.04-arm + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ggml-ci-arm64-cpu-low-perf + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Test + id: ggml-ci + env: + HF_TOKEN: ${{ secrets.HF_TOKEN }} + run: | + LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt + + ggml-ci-x64-cpu-high-perf: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ggml-ci-x64-cpu-high-perf + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Test + id: ggml-ci + env: + HF_TOKEN: ${{ secrets.HF_TOKEN }} + run: | + LLAMA_ARG_THREADS=$(nproc) bash ./ci/run.sh ./tmp/results ./tmp/mnt + + ggml-ci-arm64-cpu-high-perf: + runs-on: ubuntu-22.04-arm + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ggml-ci-arm64-cpu-high-perf + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Test + id: ggml-ci + env: + HF_TOKEN: ${{ secrets.HF_TOKEN }} + run: | + LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt + + ggml-ci-arm64-cpu-high-perf-sve: + runs-on: ubuntu-22.04-arm + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: ggml-ci-arm64-cpu-high-perf-sve + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Dependencies + id: depends + run: | + sudo apt-get update + sudo apt-get install build-essential libcurl4-openssl-dev + + - name: Test + id: ggml-ci + env: + HF_TOKEN: ${{ secrets.HF_TOKEN }} + run: | + LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt diff --git a/.github/workflows/build-freebsd.yml b/.github/workflows/build-freebsd.yml new file mode 100644 index 000000000..847ae975e --- /dev/null +++ b/.github/workflows/build-freebsd.yml @@ -0,0 +1,47 @@ +name: CI (freebsd) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-freebsd.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.in', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + freeBSD-latest: + runs-on: macos-13 + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Build + uses: cross-platform-actions/action@v0.27.0 + with: + operating_system: freebsd + version: '14.2' + run: | + sudo pkg update + sudo pkg install -y gmake sdl2 cmake git + cmake -B build + cmake --build build --config Release diff --git a/.github/workflows/build-gcc.yml b/.github/workflows/build-gcc.yml new file mode 100644 index 000000000..4528ba3d5 --- /dev/null +++ b/.github/workflows/build-gcc.yml @@ -0,0 +1,166 @@ +name: CI (gcc) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-gcc.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.in', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh', + '**/*.cl'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +env: + ubuntu_image: "ubuntu:22.04" + +jobs: + ubuntu-22-gcc: + runs-on: ubuntu-22.04 + + strategy: + fail-fast: false + matrix: + build: [Debug, Release] + arch: [linux/amd64, linux/ppc64le] + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Set CCACHE_DIR + run: echo "CCACHE_DIR=${{ runner.temp }}/ccache" >> $GITHUB_ENV + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: gcc-${{ matrix.arch }}-${{ matrix.build }} + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Set up QEMU + uses: docker/setup-qemu-action@v3 + + - name: Build ${{ matrix.arch }} + run: | + docker run --platform ${{ matrix.arch }} --rm \ + -v ${{ github.workspace }}:/workspace \ + -v ${CCACHE_DIR}:${CCACHE_DIR} \ + -e CCACHE_DIR=${CCACHE_DIR} \ + -w /workspace ${{ env.ubuntu_image }} /bin/sh -c ' + set -e + export DEBIAN_FRONTEND=noninteractive + sed -i "s|archive.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list + sed -i "s|security.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list + + apt update + apt install -y build-essential cmake libsdl2-dev git ccache + cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DCMAKE_C_COMPILER_LAUNCHER=ccache \ + -DCMAKE_CXX_COMPILER_LAUNCHER=ccache + make + ctest -L gh --output-on-failure' + + ubuntu-22-gcc-arm64: + runs-on: ubuntu-22.04-arm + + strategy: + fail-fast: false + matrix: + build: [Debug, Release] + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: gcc-arm64-${{ matrix.build }} + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Install dependencies + run: | + sudo apt-get update + sudo apt-get install -y build-essential cmake libsdl2-dev git + + - name: Configure CMake + run: | + cmake . \ + -DWHISPER_SDL2=ON \ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_NATIVE=OFF \ + -DGGML_CPU_ARM_ARCH=armv8-a + + - name: Build and Test + run: | + make + ctest -L gh --output-on-failure + + ubuntu-22-gcc-arm-v7: + runs-on: ubuntu-22.04 + + strategy: + fail-fast: false + matrix: + build: [Debug, Release] + arch: [linux/arm/v7] + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Set CCACHE_DIR + run: echo "CCACHE_DIR=${{ runner.temp }}/ccache" >> $GITHUB_ENV + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: gcc-${{ matrix.arch }}-${{ matrix.build }} + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Set up QEMU + uses: docker/setup-qemu-action@v3 + + - name: Build ${{ matrix.arch }} + run: | + docker run --platform ${{ matrix.arch }} --rm \ + -v ${{ github.workspace }}:/workspace \ + -v ${CCACHE_DIR}:${CCACHE_DIR} \ + -e CCACHE_DIR=${CCACHE_DIR} \ + -w /workspace ${{ env.ubuntu_image }} /bin/sh -c ' + set -e + export DEBIAN_FRONTEND=noninteractive + sed -i "s|archive.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list + sed -i "s|security.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list + + apt update + apt install -y build-essential cmake libsdl2-dev git ccache + cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ + -DGGML_NATIVE=OFF \ + -DGGML_CPU_ARM_ARCH=armv7-a+fp \ + -DCMAKE_C_COMPILER_LAUNCHER=ccache \ + -DCMAKE_CXX_COMPILER_LAUNCHER=ccache + make + ctest -L gh --output-on-failure' diff --git a/.github/workflows/build-macos.yml b/.github/workflows/build-macos.yml new file mode 100644 index 000000000..804f8bbb6 --- /dev/null +++ b/.github/workflows/build-macos.yml @@ -0,0 +1,72 @@ +name: CI (macOS) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-macos.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.in', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh', + '**/*.swift', + '**/*.m', + '**/*.mm', + '**/*.metal'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + macOS-latest: + runs-on: macOS-latest + + strategy: + matrix: + destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: macos-${{ matrix.destination }} + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Dependencies + run: | + brew update + cmake --version + brew install sdl2 + + - name: Build + run: | + sysctl -a + cmake -B build -G Xcode \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DWHISPER_BUILD_EXAMPLES=OFF \ + -DWHISPER_BUILD_TESTS=OFF \ + -DWHISPER_BUILD_SERVER=OFF \ + -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" + cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) diff --git a/.github/workflows/build-quantize.yml b/.github/workflows/build-quantize.yml new file mode 100644 index 000000000..8036a3a34 --- /dev/null +++ b/.github/workflows/build-quantize.yml @@ -0,0 +1,41 @@ +name: CI (quantize) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-quantize.yml', + '**/CMakeLists.txt', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + quantize: + runs-on: ubuntu-22.04 + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Test quantize + env: + HF_TOKEN: ${{ secrets.HF_TOKEN }} + run: | + ./models/download-ggml-model.sh tiny.en + cmake -B build + cmake --build build --config Release + ./build/bin/whisper-quantize models/ggml-tiny.en.bin models/ggml-tiny.en-q4_0.bin q4_0 diff --git a/.github/workflows/build-sanitize.yml b/.github/workflows/build-sanitize.yml new file mode 100644 index 000000000..9250fe810 --- /dev/null +++ b/.github/workflows/build-sanitize.yml @@ -0,0 +1,82 @@ +name: CI (sanitize) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-sanitize.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' + - 'bindings/go/**' + - 'examples/addon.node/**' + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + ubuntu-22-gcc-sanitized: + runs-on: ubuntu-22.04 + + continue-on-error: true + + strategy: + fail-fast: false + matrix: + sanitizer: [ADDRESS, THREAD, UNDEFINED] + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: sanitize-${{ matrix.sanitizer }} + evict-old-files: 1d + save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }} + + - name: Install dependencies + run: | + sudo apt-get update + sudo apt-get install -y build-essential cmake git + + - name: Build (undefined) + if: ${{ matrix.sanitizer == 'UNDEFINED' }} + run: | + cmake . -DCMAKE_BUILD_TYPE=Debug \ + -DWHISPER_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DGGML_OPENMP=OFF + make + + - name: Build + if: ${{ matrix.sanitizer == 'ADDRESS' }} + run: | + cmake . -DCMAKE_BUILD_TYPE=RelWithDebInfo \ + -DWHISPER_SANITIZE_${{ matrix.sanitizer }}=ON + make + + - name: Build (no OpenMP) + if: ${{ matrix.sanitizer == 'THREAD' }} + run: | + cmake . -DCMAKE_BUILD_TYPE=RelWithDebInfo \ + -DWHISPER_SANITIZE_${{ matrix.sanitizer }}=ON \ + -DGGML_OPENMP=OFF + make + + - name: Test + if: ${{ matrix.sanitizer != 'UNDEFINED' }} + run: | + ctest -L gh --output-on-failure diff --git a/.github/workflows/build-self-hosted.yml b/.github/workflows/build-self-hosted.yml new file mode 100644 index 000000000..3fe131b9b --- /dev/null +++ b/.github/workflows/build-self-hosted.yml @@ -0,0 +1,116 @@ +name: CI (self-hosted) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: [ + '.github/workflows/build.yml', + '**/CMakeLists.txt', + '**/.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh', + '**/*.swift', + '**/*.m', + '**/*.mm', + '**/*.metal', + '**/*.comp' + ] + + pull_request: + types: [opened, synchronize, reopened] + paths: [ + '.github/workflows/build-self-hosted.yml', + '**/CMakeLists.txt', + '**/.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh', + '**/*.swift', + '**/*.m', + '**/*.mm', + '**/*.metal', + '**/*.comp' + ] + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + gpu-cuda: + runs-on: [self-hosted, Linux, NVIDIA] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Test + id: ggml-ci + run: | + nvidia-smi + GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp + + gpu-vulkan-nvidia-cm: + runs-on: [self-hosted, Linux, NVIDIA] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Test + id: ggml-ci + run: | + vulkaninfo --summary + GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp + + gpu-vulkan-nvidia-cm2: + runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Test + id: ggml-ci + run: | + vulkaninfo --summary + GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp + + gpu-metal: + runs-on: [self-hosted, macOS, ARM64] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Test + id: ggml-ci + run: | + GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp + + gpu-vulkan: + runs-on: [self-hosted, macOS, ARM64] + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Test + id: ggml-ci + run: | + vulkaninfo --summary + GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp diff --git a/.github/workflows/build-sycl.yml b/.github/workflows/build-sycl.yml new file mode 100644 index 000000000..57aa7cc4d --- /dev/null +++ b/.github/workflows/build-sycl.yml @@ -0,0 +1,132 @@ +name: CI (sycl) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-sycl.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.in', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh', + '**/*.cl'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + ubuntu-22-cmake-sycl: + runs-on: ubuntu-22.04 + + strategy: + fail-fast: false + matrix: + dwhisper_sycl: [ON] + dcmake_c_compiler: [icx] + dcmake_cxx_compiler: [icpx] + arch: [linux/amd64, linux/arm64, linux/arm/v7, linux/ppc64le] + + continue-on-error: true + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp git + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel git + + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + mkdir build + cd build + cmake -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx .. + cmake --build . --config Release -j $(nproc) + + ubuntu-22-cmake-sycl-fp16: + runs-on: ubuntu-22.04 + + strategy: + fail-fast: false + matrix: + dwhisper_sycl: [ON] + dcmake_c_compiler: [icx] + dcmake_cxx_compiler: [icpx] + arch: [linux/amd64, linux/arm64, linux/arm/v7, linux/ppc64le] + + continue-on-error: true + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: add oneAPI to apt + shell: bash + run: | + cd /tmp + wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB + sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" + + - name: install oneAPI dpcpp compiler + shell: bash + run: | + sudo apt update + sudo apt install intel-oneapi-compiler-dpcpp-cpp git + + - name: install oneAPI MKL library + shell: bash + run: | + sudo apt install intel-oneapi-mkl-devel + + - name: Clone + id: checkout + uses: actions/checkout@v6 + + - name: Build + id: cmake_build + run: | + source /opt/intel/oneapi/setvars.sh + mkdir build + cd build + cmake -DGGML_SYCL_F16=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx .. + cmake --build . --config Release -j $(nproc) diff --git a/.github/workflows/build-vad.yml b/.github/workflows/build-vad.yml new file mode 100644 index 000000000..71e910a3f --- /dev/null +++ b/.github/workflows/build-vad.yml @@ -0,0 +1,43 @@ +name: CI (vad) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-vad.yml', + '**/CMakeLists.txt', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + vad: + runs-on: ubuntu-latest + + steps: + - name: Checkout + uses: actions/checkout@v6 + + - name: Build + shell: bash + run: | + cmake -B build + cmake --build build --config Release + + - name: Test + shell: bash + run: | + ctest -R ^test-vad$ --test-dir build --output-on-failure -VV diff --git a/.github/workflows/build-wasm.yml b/.github/workflows/build-wasm.yml new file mode 100644 index 000000000..42a9401af --- /dev/null +++ b/.github/workflows/build-wasm.yml @@ -0,0 +1,51 @@ +name: CI (wasm) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-wasm.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.in', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + emscripten: + runs-on: ubuntu-22.04 + + strategy: + matrix: + build: [Release] + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Setup emsdk + uses: mymindstorm/setup-emsdk@v14 + + - name: Verify + run: emcc -v + + - name: Build + run: | + emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} + make diff --git a/.github/workflows/build-windows.yml b/.github/workflows/build-windows.yml new file mode 100644 index 000000000..cd1591f01 --- /dev/null +++ b/.github/workflows/build-windows.yml @@ -0,0 +1,76 @@ +name: CI (windows) + +on: + workflow_dispatch: # allows manual triggering + push: + branches: + - master + paths: ['.github/workflows/build-windows.yml', + '**/CMakeLists.txt', + '**/Makefile', + '**/*.mk', + '**/*.cmake', + '**/*.in', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp', + '**/*.cu', + '**/*.cuh', + '**/*.cl'] + + pull_request: + types: [opened, synchronize, reopened] + paths-ignore: + - 'bindings/ruby/**' # handled by bindings-ruby.yml + - 'bindings/go/**' # handled by bindings-go.yml + - 'examples/addon.node/**' # handled by examples.yml + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +jobs: + windows-msys2: + runs-on: windows-latest + + strategy: + fail-fast: false + matrix: + include: + - { sys: UCRT64, env: ucrt-x86_64, build: Release } + - { sys: CLANG64, env: clang-x86_64, build: Release } + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Setup ${{ matrix.sys }} + uses: msys2/setup-msys2@v2 + with: + update: true + msystem: ${{matrix.sys}} + install: >- + base-devel + git + mingw-w64-${{matrix.env}}-toolchain + mingw-w64-${{matrix.env}}-cmake + mingw-w64-${{matrix.env}}-SDL2 + mingw-w64-${{matrix.env}}-openblas + + - name: Build using CMake + shell: msys2 {0} + run: | + cmake -B build -DWHISPER_SDL2=ON + cmake --build build --config ${{ matrix.build }} -j $(nproc) + + - name: Clean after building using CMake + shell: msys2 {0} + run: | + rm -rf build + + - name: Build using CMake w/ OpenBLAS + shell: msys2 {0} + run: | + cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS + cmake --build build --config ${{ matrix.build }} -j $(nproc) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml deleted file mode 100644 index b7badd510..000000000 --- a/.github/workflows/build.yml +++ /dev/null @@ -1,1573 +0,0 @@ -name: CI - -on: - push: - branches: - - master - tags: - - 'v*' - paths: ['.github/workflows/build.yml', - '**/CMakeLists.txt', - '**/Makefile', - '**/*.mk', - '**/*.cmake', - '**/*.in', - '**/*.h', - '**/*.hpp', - '**/*.c', - '**/*.cpp', - '**/*.cu', - '**/*.cuh', - '**/*.cl', - '**/*.swift', - '**/*.m', - '**/*.mm', - '**/*.metal', - '**/*.comp', - '**/*.java'] - - pull_request: - types: [opened, synchronize, reopened] - paths-ignore: - - 'bindings/ruby/**' # handled by bindings-ruby.yml - - 'bindings/go/**' # handled by bindings-go.yml - - 'examples/addon.node/**' # handled by examples.yml - workflow_dispatch: - inputs: - create_release: - description: 'Create new release' - required: true - type: boolean - pre_release_tag: - description: 'Pre-release tag name' - required: false - type: string - run_type: - description: 'Workflow type to run' - required: true - type: choice - options: - - full-ci - - release-only - -concurrency: - group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} - cancel-in-progress: true - -permissions: - contents: write # for creating release - -env: - BRANCH_NAME: ${{ github.head_ref || github.ref_name }} - ubuntu_image: "ubuntu:22.04" - VCPKG_BINARY_SOURCES: "clear;x-gha,readwrite" - -jobs: - determine-tag: - runs-on: ubuntu-latest - outputs: - tag_name: ${{ steps.tag.outputs.name }} - should_release: ${{ steps.tag.outputs.should_release }} - - steps: - - name: Checkout with full history - uses: actions/checkout@v6 - with: - fetch-depth: 0 - - - name: Determine tag name - id: tag - shell: bash - run: | - BUILD_NUMBER=$(git rev-list --count HEAD) - SHORT_HASH=$(git rev-parse --short=7 HEAD) - CUSTOM_TAG="${{ github.event.inputs.pre_release_tag }}" - SHOULD_RELEASE="false" - - echo "Raw values:" - echo "BUILD_NUMBER: $BUILD_NUMBER" - echo "SHORT_HASH: $SHORT_HASH" - echo "BRANCH_NAME: ${{ env.BRANCH_NAME }}" - echo "CUSTOM_TAG: $CUSTOM_TAG" - - if [[ "${{ github.ref_type }}" == "tag" ]]; then - echo "Using pushed tag name" - TAG_NAME="${{ github.ref_name }}" - SHOULD_RELEASE="true" - elif [[ -n "$CUSTOM_TAG" ]]; then - echo "Using custom tag" - TAG_NAME="${CUSTOM_TAG}" - SHOULD_RELEASE="true" - elif [[ "${{ github.event.inputs.create_release }}" == "true" ]]; then - echo "Manual release requested" - SHOULD_RELEASE="true" - TAG_NAME="b${BUILD_NUMBER}" - elif [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then - echo "Using master branch format" - TAG_NAME="b${BUILD_NUMBER}" - SHOULD_RELEASE="false" - else - echo "Using non-master branch format" - SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') - TAG_NAME="${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" - SHOULD_RELEASE="false" - fi - - echo "Final tag name: $TAG_NAME" - echo "Should release: $SHOULD_RELEASE" - echo "name=$TAG_NAME" >> $GITHUB_OUTPUT - echo "should_release=$SHOULD_RELEASE" >> $GITHUB_OUTPUT - - - ubuntu-22: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - fail-fast: false - matrix: - arch: [linux/amd64, linux/ppc64le] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Set up QEMU - uses: docker/setup-qemu-action@v3 - - - name: Build ${{ matrix.arch }} - run: | - docker run --platform ${{ matrix.arch }} --rm \ - -v ${{ github.workspace }}:/workspace \ - -w /workspace ${{ env.ubuntu_image }} /bin/sh -c ' - set -e - export DEBIAN_FRONTEND=noninteractive - sed -i "s|archive.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - sed -i "s|security.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - - apt update - apt install -y build-essential libsdl2-dev cmake git - cmake -B build - cmake --build build --config Release -j $(nproc)' - - ubuntu-22-arm64: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04-arm - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Install dependencies - run: | - sudo apt-get update - sudo apt-get install -y build-essential libsdl2-dev cmake git - - - name: Build - run: | - cmake -B build -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8-a - cmake --build build --config Release -j $(nproc) - - ubuntu-22-arm-v7: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - fail-fast: false - matrix: - arch: [linux/arm/v7] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Set up QEMU - uses: docker/setup-qemu-action@v3 - - - name: Build ${{ matrix.arch }} - run: | - docker run --platform ${{ matrix.arch }} --rm \ - -v ${{ github.workspace }}:/workspace \ - -w /workspace ${{ env.ubuntu_image }} /bin/sh -c ' - set -e - export DEBIAN_FRONTEND=noninteractive - sed -i "s|archive.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - sed -i "s|security.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - - apt update - apt install -y build-essential libsdl2-dev cmake git - cmake -B build -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv7-a+fp - cmake --build build --config Release -j $(nproc)' - - macOS-latest: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: macOS-latest - - strategy: - matrix: - destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS'] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: hendrikmuhs/ccache-action@v1.2.16 - with: - key: macOS-latest-swift - evict-old-files: 1d - - - name: Dependencies - run: | - brew update - cmake --version - brew install sdl2 - - - name: Build - run: | - sysctl -a - cmake -B build -G Xcode \ - -DGGML_METAL_USE_BF16=ON \ - -DGGML_METAL_EMBED_LIBRARY=ON \ - -DWHISPER_BUILD_EXAMPLES=OFF \ - -DWHISPER_BUILD_TESTS=OFF \ - -DWHISPER_BUILD_SERVER=OFF \ - -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" - cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) - - -# freeBSD-latest: -# runs-on: macos-13 -# -# steps: -# - name: Clone -# uses: actions/checkout@v6 -# -# - name: Build -# uses: cross-platform-actions/action@v0.27.0 -# with: -# operating_system: freebsd -# version: '14.2' -# run: | -# sudo pkg update -# sudo pkg install -y gmake sdl2 cmake git -# cmake -B build -# cmake --build build --config Release - - ubuntu-22-gcc: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - fail-fast: false - matrix: - build: [Debug, Release] - arch: [linux/amd64, linux/ppc64le] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Set up QEMU - uses: docker/setup-qemu-action@v3 - - - name: Build ${{ matrix.arch }} - run: | - docker run --platform ${{ matrix.arch }} --rm \ - -v ${{ github.workspace }}:/workspace \ - -w /workspace ${{ env.ubuntu_image }} /bin/sh -c ' - set -e - export DEBIAN_FRONTEND=noninteractive - sed -i "s|archive.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - sed -i "s|security.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - - apt update - apt install -y build-essential cmake libsdl2-dev git - cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} - make - ctest -L gh --output-on-failure' - - ubuntu-22-gcc-arm64: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04-arm - - strategy: - fail-fast: false - matrix: - build: [Debug, Release] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Install dependencies - run: | - sudo apt-get update - sudo apt-get install -y build-essential cmake libsdl2-dev git - - - name: Configure CMake - run: | - cmake . \ - -DWHISPER_SDL2=ON \ - -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ - -DGGML_NATIVE=OFF \ - -DGGML_CPU_ARM_ARCH=armv8-a - - - name: Build and Test - run: | - make - ctest -L gh --output-on-failure - - ubuntu-22-gcc-arm-v7: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - fail-fast: false - matrix: - build: [Debug, Release] - arch: [linux/arm/v7] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Set up QEMU - uses: docker/setup-qemu-action@v3 - - - name: Build ${{ matrix.arch }} - run: | - docker run --platform ${{ matrix.arch }} --rm \ - -v ${{ github.workspace }}:/workspace \ - -w /workspace ${{ env.ubuntu_image }} /bin/sh -c ' - set -e - export DEBIAN_FRONTEND=noninteractive - sed -i "s|archive.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - sed -i "s|security.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - - apt update - apt install -y build-essential cmake libsdl2-dev git - cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv7-a+fp - make - ctest -L gh --output-on-failure' - - ubuntu-22-clang: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - fail-fast: false - matrix: - build: [Debug, Release] - #arch: [linux/amd64, linux/arm64, linux/arm/v7, linux/ppc64le] - # TODO: arm/v7 disabled due to clang bug - # https://github.com/ggerganov/whisper.cpp/actions/runs/9657764109/job/26637633042?pr=2256#step:4:1990 - arch: [linux/amd64, linux/ppc64le] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Set up QEMU - uses: docker/setup-qemu-action@v3 - - - name: Build ${{ matrix.arch }} - run: | - docker run --platform ${{ matrix.arch }} --rm \ - -v ${{ github.workspace }}:/workspace \ - -w /workspace ${{ env.ubuntu_image }} /bin/sh -c ' - set -e - export DEBIAN_FRONTEND=noninteractive - sed -i "s|archive.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - sed -i "s|security.ubuntu.com|mirrors.kernel.org|g" /etc/apt/sources.list - - apt update - apt install -y clang build-essential cmake libsdl2-dev git - cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang - make - ctest -L gh --output-on-failure' - - ubuntu-22-clang-arm64: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04-arm - - strategy: - fail-fast: false - matrix: - build: [Debug, Release] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Install dependencies - run: | - sudo apt-get update - sudo apt-get install -y clang build-essential cmake libsdl2-dev git - - - name: Build and Test - run: | - cmake . -DWHISPER_SDL2=ON \ - -DCMAKE_BUILD_TYPE=${{ matrix.build }} \ - -DCMAKE_CXX_COMPILER=clang++ \ - -DCMAKE_C_COMPILER=clang \ - -DGGML_NATIVE=OFF \ - -DGGML_CPU_ARM_ARCH=armv8-a - make - ctest -L gh --output-on-failure - - ubuntu-22-gcc-sanitized: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - fail-fast: false - matrix: - sanitizer: [ADDRESS, THREAD, UNDEFINED] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Install dependencies - run: | - sudo apt-get update - sudo apt-get install -y build-essential cmake git - - - name: Build and Test - run: | - cmake . -DCMAKE_BUILD_TYPE=Debug \ - -DWHISPER_SANITIZE_${{ matrix.sanitizer }}=ON \ - -DGGML_OPENMP=OFF - make - ctest -L gh --output-on-failure - - ubuntu-22-cmake-sycl: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - fail-fast: false - matrix: - dwhisper_sycl: [ON] - dcmake_c_compiler: [icx] - dcmake_cxx_compiler: [icpx] - arch: [linux/amd64, linux/arm64, linux/arm/v7, linux/ppc64le] - - continue-on-error: true - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: add oneAPI to apt - shell: bash - run: | - cd /tmp - wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB - sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB - rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB - sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" - - - name: install oneAPI dpcpp compiler - shell: bash - run: | - sudo apt update - sudo apt install intel-oneapi-compiler-dpcpp-cpp git - - - name: install oneAPI MKL library - shell: bash - run: | - sudo apt install intel-oneapi-mkl-devel git - - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Build - id: cmake_build - run: | - source /opt/intel/oneapi/setvars.sh - mkdir build - cd build - cmake -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx .. - cmake --build . --config Release -j $(nproc) - - ubuntu-22-cmake-sycl-fp16: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - fail-fast: false - matrix: - dwhisper_sycl: [ON] - dcmake_c_compiler: [icx] - dcmake_cxx_compiler: [icpx] - arch: [linux/amd64, linux/arm64, linux/arm/v7, linux/ppc64le] - - continue-on-error: true - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: add oneAPI to apt - shell: bash - run: | - cd /tmp - wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB - sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB - rm GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB - sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main" - - - name: install oneAPI dpcpp compiler - shell: bash - run: | - sudo apt update - sudo apt install intel-oneapi-compiler-dpcpp-cpp git - - - name: install oneAPI MKL library - shell: bash - run: | - sudo apt install intel-oneapi-mkl-devel - - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Build - id: cmake_build - run: | - source /opt/intel/oneapi/setvars.sh - mkdir build - cd build - cmake -DGGML_SYCL_F16=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx .. - cmake --build . --config Release -j $(nproc) - - windows-msys2: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: windows-latest - - strategy: - fail-fast: false - matrix: - include: - - { sys: UCRT64, env: ucrt-x86_64, build: Release } - - { sys: CLANG64, env: clang-x86_64, build: Release } - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Setup ${{ matrix.sys }} - uses: msys2/setup-msys2@v2 - with: - update: true - msystem: ${{matrix.sys}} - install: >- - base-devel - git - mingw-w64-${{matrix.env}}-toolchain - mingw-w64-${{matrix.env}}-cmake - mingw-w64-${{matrix.env}}-SDL2 - mingw-w64-${{matrix.env}}-openblas - - - name: Build using CMake - shell: msys2 {0} - run: | - cmake -B build -DWHISPER_SDL2=ON - cmake --build build --config ${{ matrix.build }} -j $(nproc) - - - name: Clean after building using CMake - shell: msys2 {0} - run: | - rm -rf build - - - name: Build using CMake w/ OpenBLAS - shell: msys2 {0} - run: | - cmake -B build -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS - cmake --build build --config ${{ matrix.build }} -j $(nproc) - - windows: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: windows-latest - needs: determine-tag - - strategy: - matrix: - build: [Release] - arch: [Win32, x64] - sdl2: [ON] - include: - - arch: Win32 - s2arc: x86 - jnaPath: win32-x86 - - arch: x64 - s2arc: x64 - jnaPath: win32-x86-64 - - sdl2: ON - s2ver: 2.28.5 - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Add msbuild to PATH - uses: microsoft/setup-msbuild@v2 - - - name: Fetch SDL2 and set SDL2_DIR - if: matrix.sdl2 == 'ON' - run: | - C:/msys64/usr/bin/wget.exe -qO sdl2.zip https://github.com/libsdl-org/SDL/releases/download/release-${{ matrix.s2ver }}/SDL2-devel-${{ matrix.s2ver }}-VC.zip - 7z x sdl2.zip - echo "SDL2_DIR=$env:GITHUB_WORKSPACE/SDL2-${{ matrix.s2ver }}/cmake" >> $env:GITHUB_ENV - - - name: Configure - run: > - cmake -S . -B ./build -A ${{ matrix.arch }} - -DCMAKE_BUILD_TYPE=${{ matrix.build }} - -DBUILD_SHARED_LIBS=ON - -DWHISPER_SDL2=${{ matrix.sdl2 }} - -DGGML_NATIVE=OFF - -DGGML_BMI2=OFF - - - name: Build - run: | - cd ./build - msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} - - - name: Copy SDL2.dll - if: matrix.sdl2 == 'ON' - run: copy "$env:SDL2_DIR/../lib/${{ matrix.s2arc }}/SDL2.dll" build/bin/${{ matrix.build }} - - - name: Upload SDL2.dll - if: matrix.sdl2 == 'ON' - uses: actions/upload-artifact@v6 - with: - name: ${{ matrix.s2arc }}_SDL2.dll - path: build/bin/${{ matrix.build }}/SDL2.dll - - - name: Upload whisper dll - uses: actions/upload-artifact@v6 - with: - name: whisper_${{ matrix.arch }}.dll - path: build/bin/${{ matrix.build }}/whisper.dll - - - name: Upload ggml dll - uses: actions/upload-artifact@v6 - with: - name: ggml_${{ matrix.arch }}.dll - path: build/bin/${{ matrix.build }}/ggml.dll - overwrite: true - - - name: Upload ggml base dll - uses: actions/upload-artifact@v6 - with: - name: ggml_base_${{ matrix.arch }}.dll - path: build/bin/${{ matrix.build }}/ggml-base.dll - - - name: Upload ggml cpu dll - uses: actions/upload-artifact@v6 - with: - name: ggml_cpu_${{ matrix.arch }}.dll - path: build/bin/${{ matrix.build }}/ggml-cpu.dll - - - name: Pack bin artifacts - shell: pwsh - run: | - Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-bin-${{ matrix.arch }}.zip" - - - name: Upload binaries - if: matrix.sdl2 == 'ON' && ${{ needs.determine-tag.outputs.should_release }} - uses: actions/upload-artifact@v6 - with: - name: whisper-bin-${{ matrix.arch }}.zip - path: whisper-bin-${{ matrix.arch }}.zip - - windows-blas: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: windows-latest - - strategy: - matrix: - build: [Release] - arch: [Win32, x64] - blas: [ON] - sdl2: [ON] - blasver: [0.3.29] - include: - - arch: Win32 - s2arc: x86 - blasfile: x86 - - arch: x64 - s2arc: x64 - blasfile: x64_64 - - sdl2: ON - s2ver: 2.28.5 - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Export GitHub Actions cache environment variables - uses: actions/github-script@v8 - with: - script: | - core.exportVariable('ACTIONS_CACHE_URL', process.env.ACTIONS_CACHE_URL || ''); - core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || ''); - - - name: Add msbuild to PATH - uses: microsoft/setup-msbuild@v2 - - - name: Install OpenBLAS and pkgconfiglite - if: matrix.blas == 'ON' - run: | - Invoke-WebRequest "https://github.com/OpenMathLib/OpenBLAS/releases/download/v${{matrix.blasver}}/OpenBLAS-${{matrix.blasver}}_${{matrix.blasfile}}.zip" -OutFile "OpenBLAS-${{matrix.blasver}}.zip" - Expand-Archive "OpenBLAS-${{matrix.blasver}}.zip" -DestinationPath "OpenBLAS-${{matrix.blasver}}" - choco install pkgconfiglite - - - name: Fetch SDL2 and set SDL2_DIR - if: matrix.sdl2 == 'ON' - run: | - C:/msys64/usr/bin/wget.exe -qO sdl2.zip https://github.com/libsdl-org/SDL/releases/download/release-${{ matrix.s2ver }}/SDL2-devel-${{ matrix.s2ver }}-VC.zip - 7z x sdl2.zip - echo "SDL2_DIR=$env:GITHUB_WORKSPACE/SDL2-${{ matrix.s2ver }}/cmake" >> $env:GITHUB_ENV - - - name: Configure - run: > - cmake -S . -B ./build -A ${{ matrix.arch }} - -DCMAKE_TOOLCHAIN_FILE="$env:VCPKG_INSTALLATION_ROOT/scripts/buildsystems/vcpkg.cmake" - -DCMAKE_BUILD_TYPE=${{ matrix.build }} - -DGGML_BLAS=${{ matrix.blas }} - -DGGML_BLAS_VENDOR=OpenBLAS - -DBLAS_LIBRARIES="$env:GITHUB_WORKSPACE/OpenBLAS-${{matrix.blasver}}/lib/libopenblas.lib" - -DBLAS_INCLUDE_DIRS="$env:GITHUB_WORKSPACE/OpenBLAS-${{matrix.blasver}}/include" - -DWHISPER_SDL2=${{ matrix.sdl2 }} - - - name: Build - run: | - cd ./build - msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} - - - name: Copy openblas.dll - if: matrix.blas == 'ON' - run: copy "$env:GITHUB_WORKSPACE/OpenBLAS-${{matrix.blasver}}/bin/libopenblas.dll" build/bin/${{ matrix.build }} - - - name: Copy SDL2.dll - if: matrix.sdl2 == 'ON' - run: copy "$env:SDL2_DIR/../lib/${{ matrix.s2arc }}/SDL2.dll" build/bin/${{ matrix.build }} - - - name: Pack bin artifacts - shell: pwsh - run: | - Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-blas-bin-${{ matrix.arch }}.zip" - - - name: Upload binaries - if: matrix.blas == 'ON' && matrix.sdl2 == 'ON' && ${{ needs.determine-tag.outputs.should_release }} - uses: actions/upload-artifact@v6 - with: - name: whisper-blas-bin-${{ matrix.arch }}.zip - path: whisper-blas-bin-${{ matrix.arch }}.zip - - windows-cublas: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: windows-2022 - needs: determine-tag - strategy: - fail-fast: false - matrix: - build: [Release] - arch: [x64] - cublas: [ON] - sdl2: [ON] - cuda-toolkit: [12.4.0, 11.8.0] - include: - - arch: x64 - sdl2: ON - sdl2_ver: 2.28.5 - steps: - - name: Clone repository - uses: actions/checkout@v6 - - - name: Install Ninja - id: install_ninja - run: | - choco install ninja - - - name: Install ccache - uses: hendrikmuhs/ccache-action@v1.2.16 - with: - key: ${{ github.job }}-${{ matrix.cuda-toolkit }}-${{ matrix.build }} - variant: sccache - evict-old-files: 5d - - - name: Install Cuda Toolkit 11.8.0 - if: ${{ matrix.cuda-toolkit == '11.8.0' }} - run: | - $CUDA_VERSION = ${{ matrix.cuda-toolkit }} - $CUDA_TOOLKIT_DIR = "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v$CUDA_VERSION" - $CUDA_DOWNLOAD = "https://developer.download.nvidia.com/compute/cuda/redist" - - # Components versions - $CUDART_VER = "11.8.89" - $NVCC_VER = "11.8.89" - $NVRTC_VER = "11.8.89" - $CUBLAS_VER = "11.8.1.74" - $NVTX_VER = "11.8.86" - $VS_VER = "11.8.86" - $NVPROF_VER = "11.8.87" - $CCCL_VER = "11.8.89" - - # Create the directory where the CUDA Toolkit will be installed - mkdir -p $CUDA_TOOLKIT_DIR - - # Install unzip to extract the downloaded files - choco install unzip -y - - # Download all the required components - curl -O "$CUDA_DOWNLOAD/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-${CUDART_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-${NVCC_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-${NVRTC_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/libcublas/windows-x86_64/libcublas-windows-x86_64-${CUBLAS_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-${NVTX_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-${VS_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-${NVPROF_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-${CCCL_VER}-archive.zip" - - # Extract all the downloaded files to the CUDA Toolkit directory - unzip '*.zip' -d $CUDA_TOOLKIT_DIR - - # Copy all the extracted files to the main CUDA Toolkit directory - xcopy "$CUDA_TOOLKIT_DIR\cuda_cudart-windows-x86_64-${CUDART_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_nvcc-windows-x86_64-${NVCC_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_nvrtc-windows-x86_64-${NVRTC_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\libcublas-windows-x86_64-${CUBLAS_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_nvtx-windows-x86_64-${NVTX_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_nvprof-windows-x86_64-${NVPROF_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_cccl-windows-x86_64-${CCCL_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\visual_studio_integration-windows-x86_64-${VS_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - - # Visual Studio integration - xcopy "$CUDA_TOOLKIT_DIR\visual_studio_integration-windows-x86_64-${VS_VER}-archive\visual_studio_integration\MSBuildExtensions\*" "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\MSBuild\Microsoft\VC\v170\BuildCustomizations" /E /I /H /Y - - # Set environment variables - echo "$CUDA_TOOLKIT_DIR\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append - echo "$CUDA_TOOLKIT_DIR\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append - echo "CUDA_PATH=$CUDA_TOOLKIT_DIR" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 - echo "CUDA_PATH_V11_8=$CUDA_TOOLKIT_DIR" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 - - - name: Install Cuda Toolkit 12.4.0 - if: ${{ matrix.cuda-toolkit == '12.4.0' }} - run: | - $CUDA_VERSION = ${{ matrix.cuda-toolkit }} - $CUDA_TOOLKIT_DIR = "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v$CUDA_VERSION" - $CUDA_DOWNLOAD = "https://developer.download.nvidia.com/compute/cuda/redist" - - # Components versions - $CUDART_VER = "12.4.127" - $NVCC_VER = "12.4.131" - $NVRTC_VER = "12.4.127" - $CUBLAS_VER = "12.4.5.8" - $NVTX_VER = "12.4.127" - $PROFILER_VER = "12.4.127" - $VS_VER = "12.4.127" - $NVPROF_VER = "12.4.128" - $CCCL_VER = "12.4.127" - - # Create the directory where the CUDA Toolkit will be installed - mkdir -p $CUDA_TOOLKIT_DIR - - # Install unzip to extract the downloaded files - choco install unzip -y - - # Download all the required components - curl -O "$CUDA_DOWNLOAD/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-${CUDART_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-${NVCC_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-${NVRTC_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/libcublas/windows-x86_64/libcublas-windows-x86_64-${CUBLAS_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-${NVTX_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-${PROFILER_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-${VS_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-${NVPROF_VER}-archive.zip" - curl -O "$CUDA_DOWNLOAD/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-${CCCL_VER}-archive.zip" - - # Extract all the downloaded files to the CUDA Toolkit directory - unzip -q '*.zip' -d $CUDA_TOOLKIT_DIR - - # Copy all the extracted files to the main CUDA Toolkit directory - xcopy "$CUDA_TOOLKIT_DIR\cuda_cudart-windows-x86_64-${CUDART_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_nvcc-windows-x86_64-${NVCC_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_nvrtc-windows-x86_64-${NVRTC_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\libcublas-windows-x86_64-${CUBLAS_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_nvtx-windows-x86_64-${NVTX_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_nvprof-windows-x86_64-${NVPROF_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_cccl-windows-x86_64-${CCCL_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\cuda_profiler_api-windows-x86_64-${PROFILER_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - xcopy "$CUDA_TOOLKIT_DIR\visual_studio_integration-windows-x86_64-${VS_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y - - # Visual Studio integration - xcopy "$CUDA_TOOLKIT_DIR\visual_studio_integration-windows-x86_64-${VS_VER}-archive\visual_studio_integration\MSBuildExtensions\*" "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\MSBuild\Microsoft\VC\v170\BuildCustomizations" /E /I /H /Y - - # Set environment variables - echo "$CUDA_TOOLKIT_DIR\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append - echo "$CUDA_TOOLKIT_DIR\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append - echo "CUDA_PATH=$CUDA_TOOLKIT_DIR" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 - echo "CUDA_PATH_V12_2=$CUDA_TOOLKIT_DIR" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 - - - name: Add msbuild to PATH - uses: microsoft/setup-msbuild@v2 - - - name: Install 7-Zip - run: choco install 7zip -y - - - name: Fetch SDL2 and set SDL2_DIR - if: matrix.sdl2 == 'ON' - run: | - Invoke-WebRequest -Uri https://github.com/libsdl-org/SDL/releases/download/release-${{ matrix.sdl2_ver }}/SDL2-devel-${{ matrix.sdl2_ver }}-VC.zip -OutFile sdl2.zip - 7z x sdl2.zip - echo "SDL2_DIR=${{ github.workspace }}\SDL2-${{ matrix.sdl2_ver }}\cmake" | Out-File -FilePath $env:GITHUB_ENV -Append - echo "${{ github.workspace }}\SDL2-${{ matrix.sdl2_ver }}\cmake" > SDL2_PATH.txt - - - name: Install cmake - run: choco install cmake - - - name: Build Project - shell: cmd - run: | - call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat" - cmake --version - where cmake - if "${{ matrix.cuda-toolkit }}" == "11.8.0" ( - set CUDA_FLAGS=-allow-unsupported-compiler -D_ALLOW_COMPILER_AND_STL_VERSION_MISMATCH -D_DISABLE_CONSTEXPR_MUTEX_CONSTRUCTOR - ) else ( - set CUDA_FLAGS= - ) - cmake -S . -B build -G "Ninja Multi-Config" ^ - -DCMAKE_BUILD_TYPE=${{ matrix.build }} ^ - -DGGML_CUDA=${{ matrix.cublas }} ^ - -DWHISPER_SDL2=${{ matrix.sdl2 }} ^ - -DSDL2_DIR="%SDL2_DIR%" ^ - -DCMAKE_POLICY_VERSION_MINIMUM=3.5 ^ - -DCMAKE_CUDA_FLAGS="%CUDA_FLAGS%" - set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 - cmake --build build --config ${{ matrix.build }} -j %NUMBER_OF_PROCESSORS% - - - name: Check sccache status after build - run: | - sccache --show-stats - - - name: Copy CUDA DLLs - run: | - Get-ChildItem "$env:CUDA_PATH\bin\" -Filter "*.dll" | - Copy-Item -Destination "build/bin/${{ matrix.build }}" - - - name: Copy SDL2.dll - if: matrix.sdl2 == 'ON' - run: copy "$env:SDL2_DIR/../lib/${{ matrix.arch }}/SDL2.dll" build/bin/${{ matrix.build }} - - - name: Pack bin artifacts - shell: pwsh - run: | - Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-cublas-${{ matrix.cuda-toolkit }}-bin-${{ matrix.arch }}.zip" - - - name: Upload binaries - if: ${{ needs.determine-tag.outputs.should_release }} - uses: actions/upload-artifact@v6 - with: - name: whisper-cublas-${{ matrix.cuda-toolkit }}-bin-${{ matrix.arch }}.zip - path: whisper-cublas-${{ matrix.cuda-toolkit }}-bin-${{ matrix.arch }}.zip - - emscripten: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - strategy: - matrix: - build: [Release] - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Setup emsdk - uses: mymindstorm/setup-emsdk@v14 - - - name: Verify - run: emcc -v - - - name: Build - run: | - emcmake cmake . -DCMAKE_BUILD_TYPE=${{ matrix.build }} - make - - ios-xcode-build: - runs-on: macos-latest - needs: determine-tag - - strategy: - matrix: - build: [Release] - - steps: - - name: Checkout code - uses: actions/checkout@v6 - - - name: Configure - run: | - cp models/for-tests-ggml-base.en.bin models/ggml-base.en.bin - mkdir models/ggml-base.en-encoder.mlmodelc - - - name: Build - id: cmake_build - run: | - sysctl -a - mkdir build - cd build - cmake -G Xcode .. \ - -DGGML_METAL_USE_BF16=ON \ - -DGGML_METAL_EMBED_LIBRARY=ON \ - -DWHISPER_BUILD_EXAMPLES=OFF \ - -DWHISPER_BUILD_TESTS=OFF \ - -DWHISPER_BUILD_SERVER=OFF \ - -DCMAKE_SYSTEM_NAME=iOS \ - -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ - -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml - cmake --build . --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO - - - name: xcodebuild for swift package - id: xcodebuild - run: | - ./build-xcframework.sh - - - name: Build objc example - run: xcodebuild -project examples/whisper.objc/whisper.objc.xcodeproj -scheme whisper.objc -configuration ${{ matrix.build }} -sdk iphoneos CODE_SIGN_IDENTITY="" CODE_SIGNING_REQUIRED=NO FRAMEWORK_FOLDER_PATH=./build-ios build - - - name: Build swiftui example - run: xcodebuild -project examples/whisper.swiftui/whisper.swiftui.xcodeproj -scheme WhisperCppDemo -configuration ${{ matrix.build }} -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build - - - name: Pack artifacts - id: pack_artifacts - run: | - zip --symlinks -r whisper-${{ needs.determine-tag.outputs.tag_name }}-xcframework.zip build-apple/whisper.xcframework - - - name: Upload artifacts - if: ${{ needs.determine-tag.outputs.should_release }} - uses: actions/upload-artifact@v6 - with: - path: whisper-${{ needs.determine-tag.outputs.tag_name }}-xcframework.zip - name: whisper-${{ needs.determine-tag.outputs.tag_name }}-xcframework.zip - - android: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - steps: - - name: Clone - uses: actions/checkout@v6 - with: - path: whisper - - - name: Install Java - uses: actions/setup-java@v5 - with: - distribution: zulu - java-version: 21 - - - name: Setup Android SDK - uses: android-actions/setup-android@v3 - - - name: Build - run: | - cd whisper/examples/whisper.android - ./gradlew assembleRelease --no-daemon - - - name: Build with external ggml - run: | - export PATH_TO_GGML=$PWD/ggml - cd whisper/examples/whisper.android - ./gradlew assembleRelease --no-daemon - - android_java: - runs-on: ubuntu-22.04 - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: set up JDK 11 - uses: actions/setup-java@v5 - with: - java-version: '11' - distribution: 'temurin' - cache: gradle - - - name: Setup Android SDK - uses: android-actions/setup-android@v3 - with: - cmdline-tools-version: 9.0 - - - name: Build - run: | - cd examples/whisper.android.java - chmod +x ./gradlew - ./gradlew assembleRelease - - bindings-java: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - needs: ['windows'] - runs-on: windows-latest - steps: - - uses: actions/checkout@v6 - - - name: Install Java - uses: actions/setup-java@v5 - with: - distribution: zulu - java-version: 20 - - - name: Download Whisper Windows lib - uses: actions/download-artifact@v7 - with: - name: whisper_x64.dll - - - name: Download GGML Windows lib - uses: actions/download-artifact@v7 - with: - name: ggml_x64.dll - - - name: Download GGML Base Windows lib - uses: actions/download-artifact@v7 - with: - name: ggml_base_x64.dll - - - name: Download GGML CPU Windows lib - uses: actions/download-artifact@v7 - with: - name: ggml_cpu_x64.dll - - - name: Download SDL2.dll - uses: actions/download-artifact@v7 - with: - name: x64_SDL2.dll - - - name: List downloaded files - shell: pwsh - run: | - Get-ChildItem -Path "." -Recurse -Filter "*.dll" - - - name: Move DLL to correct location - shell: pwsh - run: | - New-Item -Path "build\bin\Release" -ItemType Directory -Force - - Copy-Item -Path "whisper.dll" -Destination "build\bin\Release\whisper.dll" -Force - Write-Host "Copied whisper.dll to build\bin\Release\whisper.dll directory" - - Copy-Item -Path "ggml.dll" -Destination "build\bin\Release\ggml.dll" -Force - Write-Host "Copied ggml.dll to build\bin\Release\ggml.dll directory" - - Copy-Item -Path "ggml-base.dll" -Destination "build\bin\Release\ggml-base.dll" -Force - Write-Host "Copied ggml-base.dll to build\bin\Release\ggml-base.dll directory" - - Copy-Item -Path "ggml-cpu.dll" -Destination "build\bin\Release\ggml-cpu.dll" -Force - Write-Host "Copied ggml-cpu.dll to build\bin\Release\ggml-cpu.dll directory" - - Copy-Item -Path "SDL2.dll" -Destination "build\bin\Release\SDL2.dll" -Force - Write-Host "Copied SDL2.dll to build\bin\Release\SDL2.dll directory" - - - name: List build release files - shell: pwsh - run: | - Get-ChildItem -Path "build\Release" -Recurse -Filter "*.dll" - - - name: Build - run: | - models\download-ggml-model.cmd tiny.en models/ - cd bindings/java - chmod +x ./gradlew - ./gradlew build --info - - - name: Pack jar artifacts - shell: pwsh - run: | - Compress-Archive -Path "bindings/java/build/libs/whispercpp-*.jar" -DestinationPath "whispercpp.jar.zip" - - - name: Upload jar - uses: actions/upload-artifact@v6 - with: - name: whispercpp.jar.zip - path: whispercpp.jar.zip - -# - name: Publish package -# if: ${{ github.ref == 'refs/heads/master' }} -# uses: gradle/gradle-build-action@v2.4.2 -# with: -# arguments: publish -# build-root-directory: bindings/java -# env: -# MAVEN_USERNAME: ${{ secrets.JIRA_USER }} -# MAVEN_PASSWORD: ${{ secrets.JIRA_PASS }} -# PGP_SECRET: ${{ secrets.GPG_PRIVATE_KEY }} -# PGP_PASSPHRASE: ${{ secrets.GPG_PASSPHRASE }} - - quantize: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-22.04 - - steps: - - name: Clone - uses: actions/checkout@v6 - - - name: Test quantize - run: | - ./models/download-ggml-model.sh tiny.en - cmake -B build - cmake --build build --config Release - ./build/bin/whisper-quantize models/ggml-tiny.en.bin models/ggml-tiny.en-q4_0.bin q4_0 - - release: - if: ${{ github.event.inputs.create_release == 'true' || github.event.inputs.pre_release_tag != '' || startsWith(github.ref, 'refs/tags/v') }} - - runs-on: ubuntu-latest - - needs: - - determine-tag - - ios-xcode-build - - windows - - windows-blas - - windows-cublas - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - with: - fetch-depth: 0 - - - name: ccache - uses: hendrikmuhs/ccache-action@v1.2.16 - with: - key: release - evict-old-files: 1d - - # Downloads all the artifacts from the previous jobs - - name: Download artifacts - id: download-artifact - uses: actions/download-artifact@v7 - with: - path: ./artifact - - - name: Move artifacts - id: move_artifacts - run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release - - - name: Create release - id: create_release - uses: ggml-org/action-create-release@v1 - env: - GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} - with: - tag_name: ${{ needs.determine-tag.outputs.tag_name }} - prerelease: ${{ github.event.inputs.pre_release_tag != '' }} - draft: true - - - 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/release')) { - 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/release/${file}`) - }); - } - } - - coreml-base-en: - if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') || - github.event.inputs.create_release == 'true' || - github.event.inputs.pre_release_tag != '' || - startsWith(github.ref, 'refs/tags/v') }} - runs-on: macos-latest - needs: determine-tag - - steps: - - name: Checkout code - uses: actions/checkout@v6 - - - name: Set environment variables - id: set_vars - run: | - echo "MODEL_NAME=base.en" >> $GITHUB_ENV - echo "GEN_MODEL_NAME=whisper-${{ needs.determine-tag.outputs.tag_name }}-ggml-base.en-encoder.mlmodelc" >> $GITHUB_ENV - - - name: Download model - run: | - ./models/download-ggml-model.sh ${{ env.MODEL_NAME }} - - - name: Generate CoreML model - run: | - python3.11 -m venv venv - source venv/bin/activate - pip install ane_transformers openai-whisper coremltools - ./models/generate-coreml-model.sh ${{ env.MODEL_NAME }} - - vad: - if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' || - github.event.inputs.run_type == 'full-ci' }} - runs-on: ubuntu-latest - - steps: - - name: Checkout - uses: actions/checkout@v6 - - - name: Build - shell: bash - run: | - cmake -B build - cmake --build build --config Release - - - name: Test - shell: bash - run: | - ctest -R ^test-vad$ --test-dir build --output-on-failure -VV - -# TODO: simplify the following workflows using a matrix - ggml-ci-x64-cpu-low-perf: - runs-on: ubuntu-22.04 - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: ggml-org/ccache-action@v1.2.16 - with: - key: ggml-ci-x64-cpu-low-perf - evict-old-files: 1d - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential libcurl4-openssl-dev - - - name: Test - id: ggml-ci - run: | - LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt - - ggml-ci-arm64-cpu-low-perf: - runs-on: ubuntu-22.04-arm - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: ggml-org/ccache-action@v1.2.16 - with: - key: ggml-ci-arm64-cpu-low-perf - evict-old-files: 1d - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential libcurl4-openssl-dev - - - name: Test - id: ggml-ci - run: | - LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt - - ggml-ci-x64-cpu-high-perf: - runs-on: ubuntu-22.04 - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: ggml-org/ccache-action@v1.2.16 - with: - key: ggml-ci-x64-cpu-high-perf - evict-old-files: 1d - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential libcurl4-openssl-dev - - - name: Test - id: ggml-ci - run: | - LLAMA_ARG_THREADS=$(nproc) bash ./ci/run.sh ./tmp/results ./tmp/mnt - - ggml-ci-arm64-cpu-high-perf: - runs-on: ubuntu-22.04-arm - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: ggml-org/ccache-action@v1.2.16 - with: - key: ggml-ci-arm64-cpu-high-perf - evict-old-files: 1d - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential libcurl4-openssl-dev - - - name: Test - id: ggml-ci - run: | - LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt - - ggml-ci-arm64-cpu-high-perf-sve: - runs-on: ubuntu-22.04-arm - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: ccache - uses: ggml-org/ccache-action@v1.2.16 - with: - key: ggml-ci-arm64-cpu-high-perf-sve - evict-old-files: 1d - - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get install build-essential libcurl4-openssl-dev - - - name: Test - id: ggml-ci - run: | - LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt - - ggml-ci-x64-nvidia-cuda: - runs-on: [self-hosted, Linux, NVIDIA] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - nvidia-smi - GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp - - ggml-ci-x64-nvidia-vulkan-cm: - runs-on: [self-hosted, Linux, NVIDIA] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - vulkaninfo --summary - GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp - - ggml-ci-x64-nvidia-vulkan-cm2: - runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - vulkaninfo --summary - GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp - - #ggml-ci-x64-cpu-amx: - # runs-on: [self-hosted, Linux, X64, CPU, AMX] - - # steps: - # - name: Clone - # id: checkout - # uses: actions/checkout@v6 - - # - name: Test - # id: ggml-ci - # run: | - # bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp - - ggml-ci-mac-metal: - runs-on: [self-hosted, macOS, ARM64] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp - - ggml-ci-mac-vulkan: - runs-on: [self-hosted, macOS, ARM64] - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v6 - - - name: Test - id: ggml-ci - run: | - vulkaninfo --summary - GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/whisper.cpp ~/mnt/whisper.cpp diff --git a/.github/workflows/examples.yml b/.github/workflows/examples.yml index df3aa832c..eaa4fe4df 100644 --- a/.github/workflows/examples.yml +++ b/.github/workflows/examples.yml @@ -42,6 +42,8 @@ jobs: run: npx cmake-js compile -T addon.node -B Release - name: Download test model + env: + HF_TOKEN: ${{ secrets.HF_TOKEN }} run: | bash ./models/download-ggml-model.sh base.en - name: Test diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml new file mode 100644 index 000000000..2ba8b4509 --- /dev/null +++ b/.github/workflows/release.yml @@ -0,0 +1,649 @@ +name: Release + +on: + workflow_dispatch: + inputs: + create_release: + description: 'Create new release' + required: true + type: boolean + pre_release_tag: + description: 'Pre-release tag name' + required: false + type: string + + push: + branches: + - master + tags: + - 'v*' + +env: + BRANCH_NAME: ${{ github.head_ref || github.ref_name }} + VCPKG_BINARY_SOURCES: "clear;x-gha,readwrite" + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} + cancel-in-progress: true + +permissions: + contents: write # for creating release + +jobs: + determine-tag: + runs-on: ubuntu-latest + outputs: + tag_name: ${{ steps.tag.outputs.name }} + should_release: ${{ steps.tag.outputs.should_release }} + + steps: + - name: Checkout with full history + uses: actions/checkout@v6 + with: + fetch-depth: 0 + + - name: Determine tag name + id: tag + shell: bash + run: | + BUILD_NUMBER=$(git rev-list --count HEAD) + SHORT_HASH=$(git rev-parse --short=7 HEAD) + CUSTOM_TAG="${{ github.event.inputs.pre_release_tag }}" + SHOULD_RELEASE="false" + + echo "Raw values:" + echo "BUILD_NUMBER: $BUILD_NUMBER" + echo "SHORT_HASH: $SHORT_HASH" + echo "BRANCH_NAME: ${{ env.BRANCH_NAME }}" + echo "CUSTOM_TAG: $CUSTOM_TAG" + + if [[ "${{ github.ref_type }}" == "tag" ]]; then + echo "Using pushed tag name" + TAG_NAME="${{ github.ref_name }}" + SHOULD_RELEASE="true" + elif [[ -n "$CUSTOM_TAG" ]]; then + echo "Using custom tag" + TAG_NAME="${CUSTOM_TAG}" + SHOULD_RELEASE="true" + elif [[ "${{ github.event.inputs.create_release }}" == "true" ]]; then + echo "Manual release requested" + SHOULD_RELEASE="true" + TAG_NAME="b${BUILD_NUMBER}" + elif [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then + echo "Using master branch format" + TAG_NAME="b${BUILD_NUMBER}" + SHOULD_RELEASE="false" + else + echo "Using non-master branch format" + SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') + TAG_NAME="${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" + SHOULD_RELEASE="false" + fi + + echo "Final tag name: $TAG_NAME" + echo "Should release: $SHOULD_RELEASE" + echo "name=$TAG_NAME" >> $GITHUB_OUTPUT + echo "should_release=$SHOULD_RELEASE" >> $GITHUB_OUTPUT + + ubuntu-cpu: + runs-on: ${{ matrix.os }} + needs: determine-tag + if: ${{ needs.determine-tag.outputs.should_release == 'true' }} + + strategy: + matrix: + include: + - build: x64 + os: ubuntu-22.04 + - build: arm64 + os: ubuntu-22.04-arm + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: release-${{ matrix.os }}-cpu + evict-old-files: 1d + + - name: Dependencies + run: | + sudo apt-get update + sudo apt-get install -y build-essential cmake + + - name: Build + run: | + cmake -B build \ + -DCMAKE_BUILD_TYPE=Release \ + -DBUILD_SHARED_LIBS=OFF \ + -DGGML_NATIVE=OFF \ + ${{ matrix.build == 'arm64' && '-DGGML_CPU_ARM_ARCH=armv8-a' || '' }} + cmake --build build --config Release -j $(nproc) + + - name: Pack artifacts + run: | + cp LICENSE ./build/bin/ + tar -czvf whisper-bin-ubuntu-${{ matrix.build }}.tar.gz \ + --transform "s,^\.,whisper-bin-ubuntu-${{ matrix.build }}," \ + -C ./build/bin . + + - name: Upload artifacts + uses: actions/upload-artifact@v6 + with: + path: whisper-bin-ubuntu-${{ matrix.build }}.tar.gz + name: whisper-bin-ubuntu-${{ matrix.build }}.tar.gz + + windows: + runs-on: windows-latest + needs: determine-tag + + strategy: + matrix: + build: [Release] + arch: [Win32, x64] + sdl2: [ON] + include: + - arch: Win32 + s2arc: x86 + jnaPath: win32-x86 + - arch: x64 + s2arc: x64 + jnaPath: win32-x86-64 + - sdl2: ON + s2ver: 2.28.5 + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Add msbuild to PATH + uses: microsoft/setup-msbuild@v2 + + - name: Fetch SDL2 and set SDL2_DIR + if: matrix.sdl2 == 'ON' + run: | + C:/msys64/usr/bin/wget.exe -qO sdl2.zip https://github.com/libsdl-org/SDL/releases/download/release-${{ matrix.s2ver }}/SDL2-devel-${{ matrix.s2ver }}-VC.zip + 7z x sdl2.zip + echo "SDL2_DIR=$env:GITHUB_WORKSPACE/SDL2-${{ matrix.s2ver }}/cmake" >> $env:GITHUB_ENV + + - name: Configure + run: > + cmake -S . -B ./build -A ${{ matrix.arch }} + -DCMAKE_BUILD_TYPE=${{ matrix.build }} + -DBUILD_SHARED_LIBS=ON + -DWHISPER_SDL2=${{ matrix.sdl2 }} + -DGGML_NATIVE=OFF + -DGGML_BMI2=OFF + + - name: Build + run: | + cd ./build + msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} + + - name: Copy SDL2.dll + if: matrix.sdl2 == 'ON' + run: copy "$env:SDL2_DIR/../lib/${{ matrix.s2arc }}/SDL2.dll" build/bin/${{ matrix.build }} + + - name: Upload SDL2.dll + if: matrix.sdl2 == 'ON' + uses: actions/upload-artifact@v6 + with: + name: ${{ matrix.s2arc }}_SDL2.dll + path: build/bin/${{ matrix.build }}/SDL2.dll + + - name: Upload whisper dll + uses: actions/upload-artifact@v6 + with: + name: whisper_${{ matrix.arch }}.dll + path: build/bin/${{ matrix.build }}/whisper.dll + + - name: Upload ggml dll + uses: actions/upload-artifact@v6 + with: + name: ggml_${{ matrix.arch }}.dll + path: build/bin/${{ matrix.build }}/ggml.dll + overwrite: true + + - name: Upload ggml base dll + uses: actions/upload-artifact@v6 + with: + name: ggml_base_${{ matrix.arch }}.dll + path: build/bin/${{ matrix.build }}/ggml-base.dll + + - name: Upload ggml cpu dll + uses: actions/upload-artifact@v6 + with: + name: ggml_cpu_${{ matrix.arch }}.dll + path: build/bin/${{ matrix.build }}/ggml-cpu.dll + + - name: Pack bin artifacts + shell: pwsh + run: | + Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-bin-${{ matrix.arch }}.zip" + + - name: Upload binaries + if: matrix.sdl2 == 'ON' && ${{ needs.determine-tag.outputs.should_release }} + uses: actions/upload-artifact@v6 + with: + name: whisper-bin-${{ matrix.arch }}.zip + path: whisper-bin-${{ matrix.arch }}.zip + + windows-blas: + runs-on: windows-latest + needs: determine-tag + + strategy: + matrix: + build: [Release] + arch: [Win32, x64] + blas: [ON] + sdl2: [ON] + blasver: [0.3.29] + include: + - arch: Win32 + s2arc: x86 + blasfile: x86 + - arch: x64 + s2arc: x64 + blasfile: x64_64 + - sdl2: ON + s2ver: 2.28.5 + + steps: + - name: Clone + uses: actions/checkout@v6 + + - name: Export GitHub Actions cache environment variables + uses: actions/github-script@v8 + with: + script: | + core.exportVariable('ACTIONS_CACHE_URL', process.env.ACTIONS_CACHE_URL || ''); + core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || ''); + + - name: Add msbuild to PATH + uses: microsoft/setup-msbuild@v2 + + - name: Install OpenBLAS and pkgconfiglite + if: matrix.blas == 'ON' + run: | + Invoke-WebRequest "https://github.com/OpenMathLib/OpenBLAS/releases/download/v${{matrix.blasver}}/OpenBLAS-${{matrix.blasver}}_${{matrix.blasfile}}.zip" -OutFile "OpenBLAS-${{matrix.blasver}}.zip" + Expand-Archive "OpenBLAS-${{matrix.blasver}}.zip" -DestinationPath "OpenBLAS-${{matrix.blasver}}" + choco install pkgconfiglite + + - name: Fetch SDL2 and set SDL2_DIR + if: matrix.sdl2 == 'ON' + run: | + C:/msys64/usr/bin/wget.exe -qO sdl2.zip https://github.com/libsdl-org/SDL/releases/download/release-${{ matrix.s2ver }}/SDL2-devel-${{ matrix.s2ver }}-VC.zip + 7z x sdl2.zip + echo "SDL2_DIR=$env:GITHUB_WORKSPACE/SDL2-${{ matrix.s2ver }}/cmake" >> $env:GITHUB_ENV + + - name: Configure + run: > + cmake -S . -B ./build -A ${{ matrix.arch }} + -DCMAKE_TOOLCHAIN_FILE="$env:VCPKG_INSTALLATION_ROOT/scripts/buildsystems/vcpkg.cmake" + -DCMAKE_BUILD_TYPE=${{ matrix.build }} + -DGGML_BLAS=${{ matrix.blas }} + -DGGML_BLAS_VENDOR=OpenBLAS + -DBLAS_LIBRARIES="$env:GITHUB_WORKSPACE/OpenBLAS-${{matrix.blasver}}/lib/libopenblas.lib" + -DBLAS_INCLUDE_DIRS="$env:GITHUB_WORKSPACE/OpenBLAS-${{matrix.blasver}}/include" + -DWHISPER_SDL2=${{ matrix.sdl2 }} + + - name: Build + run: | + cd ./build + msbuild ALL_BUILD.vcxproj -t:build -p:configuration=${{ matrix.build }} -p:platform=${{ matrix.arch }} + + - name: Copy openblas.dll + if: matrix.blas == 'ON' + run: copy "$env:GITHUB_WORKSPACE/OpenBLAS-${{matrix.blasver}}/bin/libopenblas.dll" build/bin/${{ matrix.build }} + + - name: Copy SDL2.dll + if: matrix.sdl2 == 'ON' + run: copy "$env:SDL2_DIR/../lib/${{ matrix.s2arc }}/SDL2.dll" build/bin/${{ matrix.build }} + + - name: Pack bin artifacts + shell: pwsh + run: | + Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-blas-bin-${{ matrix.arch }}.zip" + + - name: Upload binaries + if: matrix.blas == 'ON' && matrix.sdl2 == 'ON' && ${{ needs.determine-tag.outputs.should_release }} + uses: actions/upload-artifact@v6 + with: + name: whisper-blas-bin-${{ matrix.arch }}.zip + path: whisper-blas-bin-${{ matrix.arch }}.zip + + windows-cublas: + runs-on: windows-2022 + needs: determine-tag + strategy: + fail-fast: false + matrix: + build: [Release] + arch: [x64] + cublas: [ON] + sdl2: [ON] + cuda-toolkit: [12.4.0, 11.8.0] + include: + - arch: x64 + sdl2: ON + sdl2_ver: 2.28.5 + steps: + - name: Clone repository + uses: actions/checkout@v6 + + - name: Install Ninja + id: install_ninja + run: | + choco install ninja + + - name: Install ccache + uses: hendrikmuhs/ccache-action@v1.2.16 + with: + key: ${{ github.job }}-${{ matrix.cuda-toolkit }}-${{ matrix.build }} + variant: sccache + evict-old-files: 5d + + - name: Install Cuda Toolkit 11.8.0 + if: ${{ matrix.cuda-toolkit == '11.8.0' }} + run: | + $CUDA_VERSION = ${{ matrix.cuda-toolkit }} + $CUDA_TOOLKIT_DIR = "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v$CUDA_VERSION" + $CUDA_DOWNLOAD = "https://developer.download.nvidia.com/compute/cuda/redist" + + # Components versions + $CUDART_VER = "11.8.89" + $NVCC_VER = "11.8.89" + $NVRTC_VER = "11.8.89" + $CUBLAS_VER = "11.8.1.74" + $NVTX_VER = "11.8.86" + $VS_VER = "11.8.86" + $NVPROF_VER = "11.8.87" + $CCCL_VER = "11.8.89" + + # Create the directory where the CUDA Toolkit will be installed + mkdir -p $CUDA_TOOLKIT_DIR + + # Install unzip to extract the downloaded files + choco install unzip -y + + # Download all the required components + curl -O "$CUDA_DOWNLOAD/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-${CUDART_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-${NVCC_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-${NVRTC_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/libcublas/windows-x86_64/libcublas-windows-x86_64-${CUBLAS_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-${NVTX_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-${VS_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-${NVPROF_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-${CCCL_VER}-archive.zip" + + # Extract all the downloaded files to the CUDA Toolkit directory + unzip '*.zip' -d $CUDA_TOOLKIT_DIR + + # Copy all the extracted files to the main CUDA Toolkit directory + xcopy "$CUDA_TOOLKIT_DIR\cuda_cudart-windows-x86_64-${CUDART_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_nvcc-windows-x86_64-${NVCC_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_nvrtc-windows-x86_64-${NVRTC_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\libcublas-windows-x86_64-${CUBLAS_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_nvtx-windows-x86_64-${NVTX_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_nvprof-windows-x86_64-${NVPROF_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_cccl-windows-x86_64-${CCCL_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\visual_studio_integration-windows-x86_64-${VS_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + + # Visual Studio integration + xcopy "$CUDA_TOOLKIT_DIR\visual_studio_integration-windows-x86_64-${VS_VER}-archive\visual_studio_integration\MSBuildExtensions\*" "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\MSBuild\Microsoft\VC\v170\BuildCustomizations" /E /I /H /Y + + # Set environment variables + echo "$CUDA_TOOLKIT_DIR\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "$CUDA_TOOLKIT_DIR\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=$CUDA_TOOLKIT_DIR" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V11_8=$CUDA_TOOLKIT_DIR" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Install Cuda Toolkit 12.4.0 + if: ${{ matrix.cuda-toolkit == '12.4.0' }} + run: | + $CUDA_VERSION = ${{ matrix.cuda-toolkit }} + $CUDA_TOOLKIT_DIR = "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v$CUDA_VERSION" + $CUDA_DOWNLOAD = "https://developer.download.nvidia.com/compute/cuda/redist" + + # Components versions + $CUDART_VER = "12.4.127" + $NVCC_VER = "12.4.131" + $NVRTC_VER = "12.4.127" + $CUBLAS_VER = "12.4.5.8" + $NVTX_VER = "12.4.127" + $PROFILER_VER = "12.4.127" + $VS_VER = "12.4.127" + $NVPROF_VER = "12.4.128" + $CCCL_VER = "12.4.127" + + # Create the directory where the CUDA Toolkit will be installed + mkdir -p $CUDA_TOOLKIT_DIR + + # Install unzip to extract the downloaded files + choco install unzip -y + + # Download all the required components + curl -O "$CUDA_DOWNLOAD/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-${CUDART_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-${NVCC_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-${NVRTC_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/libcublas/windows-x86_64/libcublas-windows-x86_64-${CUBLAS_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-${NVTX_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-${PROFILER_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-${VS_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-${NVPROF_VER}-archive.zip" + curl -O "$CUDA_DOWNLOAD/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-${CCCL_VER}-archive.zip" + + # Extract all the downloaded files to the CUDA Toolkit directory + unzip -q '*.zip' -d $CUDA_TOOLKIT_DIR + + # Copy all the extracted files to the main CUDA Toolkit directory + xcopy "$CUDA_TOOLKIT_DIR\cuda_cudart-windows-x86_64-${CUDART_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_nvcc-windows-x86_64-${NVCC_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_nvrtc-windows-x86_64-${NVRTC_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\libcublas-windows-x86_64-${CUBLAS_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_nvtx-windows-x86_64-${NVTX_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_nvprof-windows-x86_64-${NVPROF_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_cccl-windows-x86_64-${CCCL_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\cuda_profiler_api-windows-x86_64-${PROFILER_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + xcopy "$CUDA_TOOLKIT_DIR\visual_studio_integration-windows-x86_64-${VS_VER}-archive\*" "$CUDA_TOOLKIT_DIR" /E /I /H /Y + + # Visual Studio integration + xcopy "$CUDA_TOOLKIT_DIR\visual_studio_integration-windows-x86_64-${VS_VER}-archive\visual_studio_integration\MSBuildExtensions\*" "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\MSBuild\Microsoft\VC\v170\BuildCustomizations" /E /I /H /Y + + # Set environment variables + echo "$CUDA_TOOLKIT_DIR\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "$CUDA_TOOLKIT_DIR\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append + echo "CUDA_PATH=$CUDA_TOOLKIT_DIR" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + echo "CUDA_PATH_V12_2=$CUDA_TOOLKIT_DIR" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8 + + - name: Add msbuild to PATH + uses: microsoft/setup-msbuild@v2 + + - name: Install 7-Zip + run: choco install 7zip -y + + - name: Fetch SDL2 and set SDL2_DIR + if: matrix.sdl2 == 'ON' + run: | + Invoke-WebRequest -Uri https://github.com/libsdl-org/SDL/releases/download/release-${{ matrix.sdl2_ver }}/SDL2-devel-${{ matrix.sdl2_ver }}-VC.zip -OutFile sdl2.zip + 7z x sdl2.zip + echo "SDL2_DIR=${{ github.workspace }}\SDL2-${{ matrix.sdl2_ver }}\cmake" | Out-File -FilePath $env:GITHUB_ENV -Append + echo "${{ github.workspace }}\SDL2-${{ matrix.sdl2_ver }}\cmake" > SDL2_PATH.txt + + - name: Install cmake + run: choco install cmake + + - name: Build Project + shell: cmd + run: | + call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat" + cmake --version + where cmake + if "${{ matrix.cuda-toolkit }}" == "11.8.0" ( + set CUDA_FLAGS=-allow-unsupported-compiler -D_ALLOW_COMPILER_AND_STL_VERSION_MISMATCH -D_DISABLE_CONSTEXPR_MUTEX_CONSTRUCTOR + ) else ( + set CUDA_FLAGS= + ) + cmake -S . -B build -G "Ninja Multi-Config" ^ + -DCMAKE_BUILD_TYPE=${{ matrix.build }} ^ + -DGGML_CUDA=${{ matrix.cublas }} ^ + -DWHISPER_SDL2=${{ matrix.sdl2 }} ^ + -DSDL2_DIR="%SDL2_DIR%" ^ + -DCMAKE_POLICY_VERSION_MINIMUM=3.5 ^ + -DCMAKE_CUDA_FLAGS="%CUDA_FLAGS%" + set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 + cmake --build build --config ${{ matrix.build }} -j %NUMBER_OF_PROCESSORS% + + - name: Check sccache status after build + run: | + sccache --show-stats + + - name: Copy CUDA DLLs + run: | + Get-ChildItem "$env:CUDA_PATH\bin\" -Filter "*.dll" | + Copy-Item -Destination "build/bin/${{ matrix.build }}" + + - name: Copy SDL2.dll + if: matrix.sdl2 == 'ON' + run: copy "$env:SDL2_DIR/../lib/${{ matrix.arch }}/SDL2.dll" build/bin/${{ matrix.build }} + + - name: Pack bin artifacts + shell: pwsh + run: | + Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-cublas-${{ matrix.cuda-toolkit }}-bin-${{ matrix.arch }}.zip" + + - name: Upload binaries + if: ${{ needs.determine-tag.outputs.should_release }} + uses: actions/upload-artifact@v6 + with: + name: whisper-cublas-${{ matrix.cuda-toolkit }}-bin-${{ matrix.arch }}.zip + path: whisper-cublas-${{ matrix.cuda-toolkit }}-bin-${{ matrix.arch }}.zip + + ios-xcode-build: + runs-on: macos-latest + needs: determine-tag + + strategy: + matrix: + build: [Release] + + steps: + - name: Checkout code + uses: actions/checkout@v6 + + - name: Configure + run: | + cp models/for-tests-ggml-base.en.bin models/ggml-base.en.bin + mkdir models/ggml-base.en-encoder.mlmodelc + + - name: Build + id: cmake_build + run: | + sysctl -a + mkdir build + cd build + cmake -G Xcode .. \ + -DGGML_METAL_USE_BF16=ON \ + -DGGML_METAL_EMBED_LIBRARY=ON \ + -DWHISPER_BUILD_EXAMPLES=OFF \ + -DWHISPER_BUILD_TESTS=OFF \ + -DWHISPER_BUILD_SERVER=OFF \ + -DCMAKE_SYSTEM_NAME=iOS \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \ + -DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml + cmake --build . --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO + + - name: xcodebuild for swift package + id: xcodebuild + run: | + ./build-xcframework.sh + + - name: Build objc example + run: xcodebuild -project examples/whisper.objc/whisper.objc.xcodeproj -scheme whisper.objc -configuration ${{ matrix.build }} -sdk iphoneos CODE_SIGN_IDENTITY="" CODE_SIGNING_REQUIRED=NO FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Build swiftui example + run: xcodebuild -project examples/whisper.swiftui/whisper.swiftui.xcodeproj -scheme WhisperCppDemo -configuration ${{ matrix.build }} -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build + + - name: Pack artifacts + id: pack_artifacts + run: | + zip --symlinks -r whisper-${{ needs.determine-tag.outputs.tag_name }}-xcframework.zip build-apple/whisper.xcframework + + - name: Upload artifacts + if: ${{ needs.determine-tag.outputs.should_release }} + uses: actions/upload-artifact@v6 + with: + path: whisper-${{ needs.determine-tag.outputs.tag_name }}-xcframework.zip + name: whisper-${{ needs.determine-tag.outputs.tag_name }}-xcframework.zip + + release: + if: ${{ github.event.inputs.create_release == 'true' || github.event.inputs.pre_release_tag != '' || startsWith(github.ref, 'refs/tags/v') }} + + runs-on: ubuntu-latest + + needs: + - determine-tag + - ubuntu-cpu + - ios-xcode-build + - windows + - windows-blas + - windows-cublas + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v6 + with: + fetch-depth: 0 + + - name: ccache + uses: ggml-org/ccache-action@v1.2.21 + with: + key: release + evict-old-files: 1d + + # Downloads all the artifacts from the previous jobs + - name: Download artifacts + id: download-artifact + uses: actions/download-artifact@v7 + with: + path: ./artifact + + - name: Move artifacts + id: move_artifacts + run: mkdir -p ./artifact/release && mv ./artifact/*/*.zip ./artifact/release && mv ./artifact/*/*.tar.gz ./artifact/release 2>/dev/null || true + + - name: Create release + id: create_release + uses: ggml-org/action-create-release@v1 + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + with: + tag_name: ${{ needs.determine-tag.outputs.tag_name }} + prerelease: ${{ github.event.inputs.pre_release_tag != '' }} + draft: true + + - 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/release')) { + if (path.extname(file) === '.zip' || file.endsWith('.tar.gz')) { + 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/release/${file}`) + }); + } + } diff --git a/ci/run.sh b/ci/run.sh index b03fdf1c6..dca4476a0 100644 --- a/ci/run.sh +++ b/ci/run.sh @@ -151,8 +151,15 @@ function gg_download_model { local cwd=`pwd` mkdir -p "$MNT/models" cd "$MNT/models" + set -x bash "$cwd/models/download-ggml-model.sh" ${model_name} . + local download_status=$? + set +x cd "$cwd" + if [ $download_status -ne 0 ]; then + echo "Error: failed to download model ${model_name}" + ret=1 + fi fi } diff --git a/models/download-ggml-model.sh b/models/download-ggml-model.sh index f1394e984..0539c8afb 100755 --- a/models/download-ggml-model.sh +++ b/models/download-ggml-model.sh @@ -120,7 +120,13 @@ fi if [ -x "$(command -v wget2)" ]; then wget2 --no-config --progress bar -O ggml-"$model".bin $src/$pfx-"$model".bin elif [ -x "$(command -v curl)" ]; then - curl -L --output ggml-"$model".bin $src/$pfx-"$model".bin + curl -L --fail \ + --retry 5 \ + --retry-delay 5 \ + --retry-all-errors \ + --retry-connrefused \ + ${HF_TOKEN:+--header "Authorization: Bearer $HF_TOKEN"} \ + --output ggml-"$model".bin $src/$pfx-"$model".bin elif [ -x "$(command -v wget)" ]; then wget --no-config --quiet --show-progress -O ggml-"$model".bin $src/$pfx-"$model".bin else