Test model fast workflow (microsoft/Olive)

# This job is run as a github action.
# It checks Olive works on random and small models.
name: Test model fast
 
on:
  workflow_dispatch:
  push:
    branches:
      - main
  pull_request:
    branches:
      - main
 
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true
 
jobs:
  ubuntu-test-model-fast:
    timeout-minutes: 30
    name: Ubuntu test model fast
    runs-on: latchkey-small
    permissions:
      contents: read
    steps:
      - uses: actions/checkout@v4
 
      - name: Setup Python
        uses: actions/setup-python@v5
        with:
          cache: 'pip'
          python-version: "3.12"
 
      - name: Install dependencies
        run: |
          python -m pip install -r requirements.txt
          python -m pip install -r test/requirements-test-cpu.txt
 
      - name: Create llama_env and install llama-cpp-python
        run: |
          LLAMA_ENV="$(pwd)/llama_env"
          python -m venv "$LLAMA_ENV"
          "$LLAMA_ENV/bin/pip" install --upgrade pip
          "$LLAMA_ENV/bin/pip" install gguf safetensors llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
          "$LLAMA_ENV/bin/pip" install transformers sentencepiece protobuf tabulate gguf
          git clone --depth=1 --filter=blob:none --sparse https://github.com/ggerganov/llama.cpp.git /tmp/llama_cpp_repo
          git -C /tmp/llama_cpp_repo sparse-checkout set convert_hf_to_gguf.py conversion --skip-checks
          cp /tmp/llama_cpp_repo/convert_hf_to_gguf.py "$LLAMA_ENV/"
          cp -r /tmp/llama_cpp_repo/conversion "$LLAMA_ENV/"
 
      - name: pip freeze
        run: |
          python -m pip freeze
 
      - name: Run fast test
        run: |
          python -m pytest -v -s -p no:warnings --disable-warnings --log-cli-level=WARNING test/cli/test_cli_test_model_smoke.py test/cli/test_cli_whisper_smoke.py