mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-30 17:52:35 +06:00
Commont bot CI for other jobs (generation
/ quantization
) (#35341)
* quantization CI on PRs * fix * fix * add 2 members --------- Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
parent
a93b80588b
commit
f19bfa50e7
164
.github/workflows/self-comment-ci.yml
vendored
164
.github/workflows/self-comment-ci.yml
vendored
@ -30,7 +30,7 @@ jobs:
|
||||
runs-on: ubuntu-22.04
|
||||
name: Get PR number
|
||||
# For security: only allow team members to run
|
||||
if: ${{ github.event.issue.state == 'open' && contains(fromJSON('["ydshieh", "ArthurZucker", "zucchini-nlp", "qubvel", "molbap", "gante", "LysandreJik", "Cyrilvallez", "Rocketknight1"]'), github.actor) && (startsWith(github.event.comment.body, 'run-slow') || startsWith(github.event.comment.body, 'run slow') || startsWith(github.event.comment.body, 'run_slow')) }}
|
||||
if: ${{ github.event.issue.state == 'open' && contains(fromJSON('["ydshieh", "ArthurZucker", "zucchini-nlp", "qubvel", "molbap", "gante", "LysandreJik", "Cyrilvallez", "Rocketknight1", "SunMarc", "muellerzr"]'), github.actor) && (startsWith(github.event.comment.body, 'run-slow') || startsWith(github.event.comment.body, 'run slow') || startsWith(github.event.comment.body, 'run_slow')) }}
|
||||
outputs:
|
||||
PR_NUMBER: ${{ steps.set_pr_number.outputs.PR_NUMBER }}
|
||||
steps:
|
||||
@ -98,6 +98,7 @@ jobs:
|
||||
if: ${{ needs.get-pr-number.outputs.PR_NUMBER != ''}}
|
||||
outputs:
|
||||
models: ${{ steps.models_to_run.outputs.models }}
|
||||
quantizations: ${{ steps.models_to_run.outputs.quantizations }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
@ -121,6 +122,8 @@ jobs:
|
||||
python -m pip install GitPython
|
||||
python utils/pr_slow_ci_models.py --message "$PR_COMMENT" | tee output.txt
|
||||
echo "models=$(tail -n 1 output.txt)" >> $GITHUB_ENV
|
||||
python utils/pr_slow_ci_models.py --message "$PR_COMMENT" --quantization | tee output2.txt
|
||||
echo "quantizations=$(tail -n 1 output2.txt)" >> $GITHUB_ENV
|
||||
|
||||
- name: Show models to test
|
||||
id: models_to_run
|
||||
@ -128,10 +131,12 @@ jobs:
|
||||
echo "${{ env.models }}"
|
||||
echo "models=${{ env.models }}" >> $GITHUB_ENV
|
||||
echo "models=${{ env.models }}" >> $GITHUB_OUTPUT
|
||||
echo "${{ env.quantizations }}"
|
||||
echo "quantizations=${{ env.quantizations }}" >> $GITHUB_OUTPUT
|
||||
|
||||
reply_to_comment:
|
||||
name: Reply to the comment
|
||||
if: ${{ needs.get-tests.outputs.models != '[]' }}
|
||||
if: ${{ needs.get-tests.outputs.models != '[]' || needs.get-tests.outputs.quantizations != '[]' }}
|
||||
needs: [get-pr-number, get-tests]
|
||||
permissions:
|
||||
pull-requests: write
|
||||
@ -141,17 +146,18 @@ jobs:
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
MODELS: ${{ needs.get-tests.outputs.models }}
|
||||
BODY: "This comment contains run-slow, running the specified jobs:\n\nmodels: ${{ needs.get-tests.outputs.models }}\nquantizations: ${{ needs.get-tests.outputs.quantizations }}"
|
||||
run: |
|
||||
gh api \
|
||||
--method POST \
|
||||
-H "Accept: application/vnd.github+json" \
|
||||
-H "X-GitHub-Api-Version: 2022-11-28" \
|
||||
repos/${{ github.repository }}/issues/${{ needs.get-pr-number.outputs.PR_NUMBER }}/comments \
|
||||
-f "body=This comment contains run-slow, running the specified jobs: ${{ env.MODELS }} ..."
|
||||
-f "body=This comment contains run-slow, running the specified jobs: ${{ env.BODY }} ..."
|
||||
|
||||
create_run:
|
||||
name: Create run
|
||||
if: ${{ needs.get-tests.outputs.models != '[]' }}
|
||||
if: ${{ needs.get-tests.outputs.models != '[]' || needs.get-tests.outputs.quantizations != '[]' }}
|
||||
needs: [get-sha, get-tests, reply_to_comment]
|
||||
permissions:
|
||||
statuses: write
|
||||
@ -173,20 +179,20 @@ jobs:
|
||||
-f "target_url=$GITHUB_RUN_URL" -f "state=pending" -f "description=Slow CI job" -f "context=pytest/custom-tests"
|
||||
|
||||
run_models_gpu:
|
||||
name: Run all tests for the model
|
||||
if: ${{ needs.get-tests.outputs.models != '[]' }}
|
||||
needs: [get-pr-number, get-sha, get-tests, create_run]
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
folders: ${{ fromJson(needs.get-tests.outputs.models) }}
|
||||
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
|
||||
runs-on:
|
||||
group: '${{ matrix.machine_type }}'
|
||||
container:
|
||||
image: huggingface/transformers-all-latest-gpu
|
||||
options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
|
||||
steps:
|
||||
name: Run all tests for the model
|
||||
if: ${{ needs.get-tests.outputs.models != '[]' }}
|
||||
needs: [get-pr-number, get-sha, get-tests, create_run]
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
folders: ${{ fromJson(needs.get-tests.outputs.models) }}
|
||||
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
|
||||
runs-on:
|
||||
group: '${{ matrix.machine_type }}'
|
||||
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: |
|
||||
@ -206,20 +212,19 @@ jobs:
|
||||
- name: Checkout to PR merge commit
|
||||
working-directory: /transformers
|
||||
run: |
|
||||
git fetch origin refs/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge:refs/remotes/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge
|
||||
git checkout refs/remotes/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge
|
||||
git log -1 --format=%H
|
||||
git fetch origin refs/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge:refs/remotes/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge
|
||||
git checkout refs/remotes/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge
|
||||
git log -1 --format=%H
|
||||
|
||||
- name: Verify merge commit SHA
|
||||
env:
|
||||
VERIFIED_PR_MERGE_SHA: ${{ needs.get-sha.outputs.PR_MERGE_SHA }}
|
||||
working-directory: /transformers
|
||||
run: |
|
||||
PR_MERGE_SHA=$(git log -1 --format=%H)
|
||||
if [ $PR_MERGE_SHA != $VERIFIED_PR_MERGE_SHA ]; then
|
||||
echo "The merged commit SHA is not the same as the verified one! Security issue detected, abort the workflow!";
|
||||
exit -1;
|
||||
fi
|
||||
PR_MERGE_SHA=$(git log -1 --format=%H)
|
||||
if [ $PR_MERGE_SHA != $VERIFIED_PR_MERGE_SHA ]; then
|
||||
echo "The merged commit SHA is not the same as the verified one! Security issue detected, abort the workflow!";
|
||||
exit -1;
|
||||
|
||||
- name: Reinstall transformers in edit mode (remove the one installed during docker image build)
|
||||
working-directory: /transformers
|
||||
@ -279,9 +284,105 @@ jobs:
|
||||
name: ${{ env.machine_type }}_run_models_gpu_${{ env.matrix_folders }}_test_reports
|
||||
path: /transformers/reports/${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports
|
||||
|
||||
run_quantization_torch_gpu:
|
||||
name: Run all tests for a quantization
|
||||
if: ${{ needs.get-tests.outputs.quantizations != '[]' }}
|
||||
needs: [get-pr-number, get-sha, get-tests, create_run]
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
folders: ${{ fromJson(needs.get-tests.outputs.quantizations) }}
|
||||
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
|
||||
runs-on:
|
||||
group: '${{ matrix.machine_type }}'
|
||||
container:
|
||||
image: huggingface/transformers-quantization-latest-gpu
|
||||
options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
|
||||
steps:
|
||||
- name: Echo folder ${{ matrix.folders }}
|
||||
shell: bash
|
||||
run: |
|
||||
echo "${{ matrix.folders }}"
|
||||
matrix_folders=${{ matrix.folders }}
|
||||
matrix_folders=${matrix_folders/'quantization/'/'quantization_'}
|
||||
echo "$matrix_folders"
|
||||
echo "matrix_folders=$matrix_folders" >> $GITHUB_ENV
|
||||
|
||||
- name: Checkout to PR merge commit
|
||||
working-directory: /transformers
|
||||
run: |
|
||||
git fetch origin refs/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge:refs/remotes/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge
|
||||
git checkout refs/remotes/pull/${{ needs.get-pr-number.outputs.PR_NUMBER }}/merge
|
||||
git log -1 --format=%H
|
||||
|
||||
- name: Verify merge commit SHA
|
||||
env:
|
||||
VERIFIED_PR_MERGE_SHA: ${{ needs.get-sha.outputs.PR_MERGE_SHA }}
|
||||
working-directory: /transformers
|
||||
run: |
|
||||
PR_MERGE_SHA=$(git log -1 --format=%H)
|
||||
if [ $PR_MERGE_SHA != $VERIFIED_PR_MERGE_SHA ]; then
|
||||
echo "The merged commit SHA is not the same as the verified one! Security issue detected, abort the workflow!";
|
||||
exit -1;
|
||||
|
||||
- name: Reinstall transformers in edit mode (remove the one installed during docker image build)
|
||||
working-directory: /transformers
|
||||
run: python3 -m pip uninstall -y transformers && python3 -m pip install -e .
|
||||
- name: NVIDIA-SMI
|
||||
run: |
|
||||
nvidia-smi
|
||||
|
||||
- name: Set `machine_type` for report and artifact names
|
||||
working-directory: /transformers
|
||||
shell: bash
|
||||
run: |
|
||||
echo "${{ matrix.machine_type }}"
|
||||
if [ "${{ matrix.machine_type }}" = "aws-g4dn-2xlarge-cache" ]; then
|
||||
machine_type=single-gpu
|
||||
elif [ "${{ matrix.machine_type }}" = "aws-g4dn-12xlarge-cache" ]; then
|
||||
machine_type=multi-gpu
|
||||
else
|
||||
machine_type=${{ matrix.machine_type }}
|
||||
fi
|
||||
echo "$machine_type"
|
||||
echo "machine_type=$machine_type" >> $GITHUB_ENV
|
||||
|
||||
- name: Environment
|
||||
working-directory: /transformers
|
||||
run: |
|
||||
python3 utils/print_env.py
|
||||
|
||||
- name: Show installed libraries and their versions
|
||||
working-directory: /transformers
|
||||
run: pip freeze
|
||||
|
||||
- name: Run quantization tests on GPU
|
||||
working-directory: /transformers
|
||||
run: |
|
||||
python3 -m pytest -v --make-reports=${{ env.machine_type }}_run_quantization_torch_gpu_${{ matrix.folders }}_test_reports tests/${{ matrix.folders }}
|
||||
|
||||
- name: Failure short reports
|
||||
if: ${{ failure() }}
|
||||
continue-on-error: true
|
||||
run: cat /transformers/reports/${{ env.machine_type }}_run_quantization_torch_gpu_${{ matrix.folders }}_test_reports/failures_short.txt
|
||||
|
||||
- name: Make sure report directory exists
|
||||
shell: bash
|
||||
run: |
|
||||
mkdir -p /transformers/reports/${{ env.machine_type }}_run_quantization_gpu_${{ matrix.folders }}_test_reports
|
||||
echo "hello" > /transformers/reports/${{ env.machine_type }}_run_quantization_gpu_${{ matrix.folders }}_test_reports/hello.txt
|
||||
echo "${{ env.machine_type }}_run_quantization_gpu_${{ matrix.folders }}_test_reports"
|
||||
|
||||
- name: "Test suite reports artifacts: ${{ env.machine_type }}_run_quantization_torch_gpu_${{ env.matrix_folders }}_test_reports"
|
||||
if: ${{ always() }}
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: ${{ env.machine_type }}_run_quantization_torch_gpu_${{ env.matrix_folders }}_test_reports
|
||||
path: /transformers/reports/${{ env.machine_type }}_run_quantization_torch_gpu_${{ matrix.folders }}_test_reports
|
||||
|
||||
update_run_status:
|
||||
name: Update Check Run Status
|
||||
needs: [get-sha, create_run, run_models_gpu]
|
||||
needs: [get-sha, create_run, run_models_gpu, run_quantization_torch_gpu]
|
||||
permissions:
|
||||
statuses: write
|
||||
if: ${{ always() && needs.create_run.result == 'success' }}
|
||||
@ -289,16 +390,17 @@ jobs:
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
GITHUB_RUN_URL: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}
|
||||
STATUS_OK: ${{ contains(fromJSON('["skipped", "success"]'), needs.run_models_gpu.result) && contains(fromJSON('["skipped", "success"]'), needs.run_quantization_torch_gpu.result) }}
|
||||
steps:
|
||||
- name: Get `run_models_gpu` job status
|
||||
run: |
|
||||
echo "${{ needs.run_models_gpu.result }}"
|
||||
if [ "${{ needs.run_models_gpu.result }}" = "cancelled" ]; then
|
||||
echo "STATUS=failure" >> $GITHUB_ENV
|
||||
elif [ "${{ needs.run_models_gpu.result }}" = "skipped" ]; then
|
||||
echo "${{ needs.run_quantization_torch_gpu.result }}"
|
||||
echo $STATUS_OK
|
||||
if [ "$STATUS_OK" = "true" ]; then
|
||||
echo "STATUS=success" >> $GITHUB_ENV
|
||||
else
|
||||
echo "STATUS=${{ needs.run_models_gpu.result }}" >> $GITHUB_ENV
|
||||
echo "STATUS=failure" >> $GITHUB_ENV
|
||||
fi
|
||||
|
||||
- name: Update PR commit statuses
|
||||
|
@ -27,6 +27,7 @@ python utils/pr_slow_ci_models.py
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os.path
|
||||
import re
|
||||
import string
|
||||
from pathlib import Path
|
||||
@ -142,6 +143,7 @@ def check_model_names(model_name: str):
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--message", type=str, default="", help="The content of a comment.")
|
||||
parser.add_argument("--quantization", action="store_true", help="If we collect quantization tests")
|
||||
args = parser.parse_args()
|
||||
|
||||
new_model = get_new_model()
|
||||
@ -149,6 +151,16 @@ if __name__ == "__main__":
|
||||
models = ([] if new_model == "" else [new_model]) + specified_models
|
||||
# a guard for strange model names
|
||||
models = [model for model in models if check_model_names(model)]
|
||||
# Add "models/"
|
||||
models = [f"models/{model}" for model in models]
|
||||
print(sorted(set(models)))
|
||||
|
||||
# Add prefix
|
||||
final_list = []
|
||||
for model in models:
|
||||
if not args.quantization:
|
||||
if os.path.isdir(f"tests/models/{model}"):
|
||||
final_list.append(f"models/{model}")
|
||||
elif os.path.isdir(f"tests/{model}") and model != "quantization":
|
||||
final_list.append(model)
|
||||
elif os.path.isdir(f"tests/quantization/{model}"):
|
||||
final_list.append(f"quantization/{model}")
|
||||
|
||||
print(sorted(set(final_list)))
|
||||
|
Loading…
Reference in New Issue
Block a user