build.yml

name: CI

on:
  workflow_dispatch: # allows manual triggering
    inputs:
      create_release:
        description: 'Create new release'
        required: true
        type: boolean
  push:
    branches:
      - master
    paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp']
  pull_request:
    types: [opened, synchronize, reopened]
    paths: ['.github/workflows/build.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal', '**/*.comp']

concurrency:
  group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
  cancel-in-progress: true

# Fine-grant permission
# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
permissions:
  contents: write # for creating release

env:
  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
  GGML_NLOOP: 3
  GGML_N_THREADS: 1
  LLAMA_LOG_COLORS: 1
  LLAMA_LOG_PREFIX: 1
  LLAMA_LOG_TIMESTAMPS: 1

jobs:
  ubuntu-cpu-cmake:
    strategy:
      matrix:
        include:
          - build: 'x64'
            os: ubuntu-22.04
          - build: 'arm64'
            os: ubuntu-22.04-arm

    runs-on: ${{ matrix.os }}

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: ubuntu-cpu-cmake
          evict-old-files: 1d

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential libcurl4-openssl-dev

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DLLAMA_CURL=ON \
            -DGGML_RPC=ON
          cmake --build build --config Release -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L 'main|curl' --verbose --timeout 900

      - name: Test llama2c conversion
        id: llama2c_test
        run: |
          cd build
          echo "Fetch tokenizer"
          wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/tok512.bin
          echo "Fetch llama2c model"
          wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
          ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
          ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          cp LICENSE ./build/bin/
          cp examples/run/linenoise.cpp/LICENSE ./build/bin/LICENSE.linenoise.cpp
          zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip ./build/bin/*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.zip
          name: llama-bin-ubuntu-${{ matrix.build }}.zip

  ubuntu-latest-cmake-sanitizer:
    runs-on: ubuntu-latest

    continue-on-error: true

    strategy:
      matrix:
        sanitizer: [ADDRESS, THREAD, UNDEFINED]
        build_type: [Debug]

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: ubuntu-latest-cmake-sanitizer-${{ matrix.sanitizer }}
          evict-old-files: 1d

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential

      - name: Build
        id: cmake_build
        if: ${{ matrix.sanitizer != 'THREAD' }}
        run: |
          cmake -B build \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }}
          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)

      - name: Build (no OpenMP)
        id: cmake_build_no_openmp
        if: ${{ matrix.sanitizer == 'THREAD' }}
        run: |
          cmake -B build \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
            -DGGML_OPENMP=OFF
          cmake --build build --config ${{ matrix.build_type }} -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose --timeout 900

  ubuntu-latest-llguidance:
    runs-on: ubuntu-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. \
            -DLLAMA_FATAL_WARNINGS=ON \
            -DLLAMA_LLGUIDANCE=ON
          cmake --build . --config Release -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose --timeout 900

  ubuntu-latest-cmake-rpc:
    runs-on: ubuntu-latest

    continue-on-error: true

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: ubuntu-latest-cmake-rpc
          evict-old-files: 1d

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential

      - name: Build
        id: cmake_build
        run: |
          cmake -B build \
            -DGGML_RPC=ON
          cmake --build build --config Release -j $(nproc)

      - name: Test
        id: cmake_test
        run: |
          cd build
          ctest -L main --verbose

  ubuntu-22-cmake-sycl:
    runs-on: ubuntu-22.04

    continue-on-error: true

    steps:
      - uses: actions/checkout@v4

      - 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

      - name: install oneAPI MKL library
        shell: bash
        run: |
          sudo apt install intel-oneapi-mkl-devel

      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: ubuntu-22-cmake-sycl
          evict-old-files: 1d

      - name: Build
        id: cmake_build
        run: |
          source /opt/intel/oneapi/setvars.sh
          cmake -B build \
            -DGGML_SYCL=ON \
            -DCMAKE_C_COMPILER=icx \
            -DCMAKE_CXX_COMPILER=icpx
          cmake --build build --config Release -j $(nproc)

  ubuntu-22-cmake-sycl-fp16:
    runs-on: ubuntu-22.04

    continue-on-error: true

    steps:
      - uses: actions/checkout@v4

      - 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

      - name: install oneAPI MKL library
        shell: bash
        run: |
          sudo apt install intel-oneapi-mkl-devel

      - name: Clone
        id: checkout
        uses: actions/checkout@v4

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: ubuntu-22-cmake-sycl-fp16
          evict-old-files: 1d

      - name: Build
        id: cmake_build
        run: |
          source /opt/intel/oneapi/setvars.sh
          cmake -B build \
            -DGGML_SYCL=ON \
            -DCMAKE_C_COMPILER=icx \
            -DCMAKE_CXX_COMPILER=icpx \
            -DGGML_SYCL_F16=ON
          cmake --build build --config Release -j $(nproc)

  windows-latest-cmake-sycl:
    runs-on: windows-latest

    defaults:
      run:
        shell: bash

    env:
      WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b380d914-366b-4b77-a74a-05e3c38b3514/intel-oneapi-base-toolkit-2025.0.0.882_offline.exe
      WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel
      ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"
    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: windows-latest-cmake-sycl
          variant: sccache
          evict-old-files: 1d

      - name: Install
        run:  |
          scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL

      - name: Build
        id: cmake_build
        run:  examples/sycl/win-build-sycl.bat

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Build the release package
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          echo "cp oneAPI running time dll files in ${{ env.ONEAPI_ROOT }} to ./build/bin"

          cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_sycl_blas.5.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_core.2.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/mkl/latest/bin/mkl_tbb_thread.2.dll" ./build/bin

          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_level_zero.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_adapter_opencl.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_loader.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/ur_win_proxy_loader.dll" ./build/bin

          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/sycl8.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/svml_dispmd.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libmmd.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/compiler/latest/bin/libiomp5md.dll" ./build/bin

          cp "${{ env.ONEAPI_ROOT }}/dnnl/latest/bin/dnnl.dll" ./build/bin
          cp "${{ env.ONEAPI_ROOT }}/tbb/latest/bin/tbb12.dll" ./build/bin

          echo "cp oneAPI running time dll files to ./build/bin done"
          7z a llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip ./build/bin/*

      - name: Upload the release package
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          path: llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip
          name: llama-bin-win-sycl-x64.zip



  release:
    if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}

    runs-on: ubuntu-latest

    needs:
      - ubuntu-cpu-cmake
      - windows-latest-cmake-sycl


    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: ccache
        uses: hendrikmuhs/ccache-action@v1.2.16
        with:
          key: release
          evict-old-files: 1d

      - name: Determine tag name
        id: tag
        shell: bash
        run: |
          BUILD_NUMBER="$(git rev-list --count HEAD)"
          SHORT_HASH="$(git rev-parse --short=7 HEAD)"
          if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
            echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
          else
            SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
            echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
          fi

      - name: Download artifacts
        id: download-artifact
        uses: actions/download-artifact@v4
        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: ${{ steps.tag.outputs.name }}

      - name: Upload release
        id: upload_release
        uses: actions/github-script@v3
        with:
          github-token: ${{secrets.GITHUB_TOKEN}}
          script: |
            const path = require('path');
            const fs = require('fs');
            const release_id = '${{ steps.create_release.outputs.id }}';
            for (let file of await fs.readdirSync('./artifact/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}`)
                });
              }
            }