name: CI (self-hosted CPU backend)

on:
  workflow_dispatch: # allows manual triggering
  push:
    branches:
      - master
    paths: [
      '.github/workflows/ci-self-hosted-cpu.yml',
      'ci/run.sh',
      '**/CMakeLists.txt',
      '**/.cmake',
      '**/*.h',
      '**/*.hpp',
      '**/*.c',
      '**/*.cpp'
    ]

  pull_request:
    types: [opened, synchronize, reopened]
    paths: [
      '.github/workflows/ci-self-hosted-cpu.yml',
      'ci/run.sh',
      '**/CMakeLists.txt',
      '**/.cmake',
      'ggml/src/*',
      'ggml/src/ggml-cpu/**'
    ]

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

env:
  # note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
  HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
  GGML_NLOOP: 3
  GGML_N_THREADS: 1
  LLAMA_ARG_LOG_COLORS: 1
  LLAMA_ARG_LOG_PREFIX: 1
  LLAMA_ARG_LOG_TIMESTAMPS: 1

jobs:
  cpu-x64-high-perf:
    runs-on: [self-hosted, Linux, X64]

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v6

      - name: Test
        id: ggml-ci
        run: |
          LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

  cpu-arm64-high-perf-graviton4:
    runs-on: ah-ubuntu_24_04-c8g_8x

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v6

      - name: Dependencies
        id: depends
        run: |
          set -euxo pipefail
          sudo apt-get update
          sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
          apt-get install -y \
          build-essential \
          python3-venv \
          gpg \
          wget \
          time \
          git-lfs

          git lfs install

          # install the latest cmake
          sudo install -d /usr/share/keyrings
          wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
            | gpg --dearmor \
            | sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
          echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
            | sudo tee /etc/apt/sources.list.d/kitware.list
          sudo apt-get update
          sudo apt-get install -y cmake

      - name: Test
        id: ggml-ci
        run: |
          LLAMA_ARG_THREADS=$(nproc) \
          GG_BUILD_HIGH_PERF=1 \
          GG_BUILD_NO_BF16=1 \
          GG_BUILD_EXTRA_TESTS_0=1 \
          bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp

  # TODO: provision AMX-compatible machine
  #cpu-amx:
  #  runs-on: [self-hosted, Linux, CPU, AMX]

  #  steps:
  #    - name: Clone
  #      id: checkout
  #      uses: actions/checkout@v6

  #    - name: Test
  #      id: ggml-ci
  #      run: |
  #        bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp