transformers/.github/workflows/self-new-model-pr-caller.yml

113 lines
4.5 KiB
YAML

name: PR slow CI
on:
pull_request:
paths:
- "src/transformers/models/*/modeling_*.py"
env:
HF_HOME: /mnt/cache
TRANSFORMERS_IS_CI: yes
OMP_NUM_THREADS: 8
MKL_NUM_THREADS: 8
RUN_SLOW: yes
# For gated repositories, we still need to agree to share information on the Hub repo. page in order to get access.
# This token is created under the bot `hf-transformers-bot`.
HF_HUB_READ_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
SIGOPT_API_TOKEN: ${{ secrets.SIGOPT_API_TOKEN }}
TF_FORCE_GPU_ALLOW_GROWTH: true
RUN_PT_TF_CROSS_TESTS: 1
CUDA_VISIBLE_DEVICES: 0,1
jobs:
check_for_new_model:
runs-on: ubuntu-22.04
name: Check if a PR is a new model PR
outputs:
new_model: ${{ steps.check_new_model.outputs.new_model }}
steps:
- uses: actions/checkout@v4
with:
fetch-depth: "0"
- name: Check if there is a new model
id: check_new_model
run: |
python -m pip install GitPython
echo "new_model=$(python utils/check_if_new_model_added.py | tail -n 1)" >> $GITHUB_OUTPUT
run_models_gpu:
name: Run all tests for the new model
# Triggered if it is a new model PR and the required label is added
if: ${{ needs.check_for_new_model.outputs.new_model != '' && contains(github.event.pull_request.labels.*.name, 'single-model-run-slow') }}
needs: check_for_new_model
strategy:
fail-fast: false
matrix:
folders: ["${{ needs.check_for_new_model.outputs.new_model }}"]
machine_type: [single-gpu, multi-gpu]
runs-on: ['${{ matrix.machine_type }}', nvidia-gpu, t4, ci]
container:
image: huggingface/transformers-all-latest-gpu
options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
steps:
- name: Echo input and matrix info
shell: bash
run: |
echo "${{ matrix.folders }}"
- name: Echo folder ${{ matrix.folders }}
shell: bash
# For folders like `models/bert`, set an env. var. (`matrix_folders`) to `models_bert`, which will be used to
# set the artifact folder names (because the character `/` is not allowed).
run: |
echo "${{ matrix.folders }}"
matrix_folders=${{ matrix.folders }}
matrix_folders=${matrix_folders/'models/'/'models_'}
echo "$matrix_folders"
echo "matrix_folders=$matrix_folders" >> $GITHUB_ENV
- name: Update clone
working-directory: /transformers
run: git fetch && git fetch origin pull/${{ github.event.pull_request.number }}/head:pull/${{ github.event.pull_request.number }}/merge && git checkout pull/${{ github.event.pull_request.number }}/merge
- name: Reinstall transformers in edit mode (remove the one installed during docker image build)
working-directory: /transformers
run: python3 -m pip uninstall -y transformers && python3 -m pip install -e .
- name: NVIDIA-SMI
run: |
nvidia-smi
- name: Environment
working-directory: /transformers
run: |
python3 utils/print_env.py
- name: Show installed libraries and their versions
working-directory: /transformers
run: pip freeze
- name: Run all tests on GPU
working-directory: /transformers
run: python3 -m pytest -v -rs --make-reports=${{ matrix.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports tests/${{ matrix.folders }}
- name: Failure short reports
if: ${{ failure() }}
continue-on-error: true
run: cat /transformers/reports/${{ matrix.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports/failures_short.txt
- name: Make sure report directory exists
shell: bash
run: |
mkdir -p /transformers/reports/${{ matrix.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports
echo "hello" > /transformers/reports/${{ matrix.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports/hello.txt
echo "${{ matrix.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports"
- name: "Test suite reports artifacts: ${{ matrix.machine_type }}_run_models_gpu_${{ env.matrix_folders }}_test_reports"
if: ${{ always() }}
uses: actions/upload-artifact@v4
with:
name: ${{ matrix.machine_type }}_run_models_gpu_${{ env.matrix_folders }}_test_reports
path: /transformers/reports/${{ matrix.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports