Skip to content

Commit

Permalink
run with new images
Browse files Browse the repository at this point in the history
  • Loading branch information
ydshieh committed Oct 23, 2024
1 parent 3975194 commit c26cede
Show file tree
Hide file tree
Showing 4 changed files with 9 additions and 96 deletions.
2 changes: 1 addition & 1 deletion .github/workflows/build-docker-images.yml
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ name: Build docker images (scheduled)
on:
push:
branches:
- drop_py38_build_img
- drop_py38_build_img_x
repository_dispatch:
workflow_call:
inputs:
Expand Down
13 changes: 1 addition & 12 deletions .github/workflows/self-scheduled-caller.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ on:
- cron: "17 2 * * *"
push:
branches:
- run_scheduled_ci*
- drop_py38_build_img

jobs:
model-ci:
Expand Down Expand Up @@ -43,17 +43,6 @@ jobs:
ci_event: Daily CI
secrets: inherit

example-ci:
name: Example CI
uses: ./.github/workflows/self-scheduled.yml
with:
job: run_examples_gpu
slack_report_channel: "#transformers-ci-daily-examples"
runner: daily-ci
docker: huggingface/transformers-all-latest-gpu
ci_event: Daily CI
secrets: inherit

deepspeed-ci:
name: DeepSpeed CI
uses: ./.github/workflows/self-scheduled.yml
Expand Down
89 changes: 6 additions & 83 deletions .github/workflows/self-scheduled.yml
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ jobs:
name: Setup
strategy:
matrix:
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
machine_type: [aws-g4dn-2xlarge-cache]
runs-on:
group: '${{ matrix.machine_type }}'
container:
Expand Down Expand Up @@ -103,7 +103,7 @@ jobs:
strategy:
fail-fast: false
matrix:
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
machine_type: [aws-g4dn-2xlarge-cache]
slice_id: ${{ fromJSON(needs.setup.outputs.slice_ids) }}
uses: ./.github/workflows/model_jobs.yml
with:
Expand All @@ -120,7 +120,7 @@ jobs:
strategy:
fail-fast: false
matrix:
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
machine_type: [aws-g4dn-2xlarge-cache]
runs-on:
group: '${{ matrix.machine_type }}'
container:
Expand Down Expand Up @@ -188,7 +188,7 @@ jobs:
strategy:
fail-fast: false
matrix:
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
machine_type: [aws-g4dn-2xlarge-cache]
runs-on:
group: '${{ matrix.machine_type }}'
container:
Expand Down Expand Up @@ -326,7 +326,7 @@ jobs:
strategy:
fail-fast: false
matrix:
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
machine_type: [aws-g4dn-2xlarge-cache]
runs-on:
group: '${{ matrix.machine_type }}'
container:
Expand Down Expand Up @@ -425,7 +425,7 @@ jobs:
fail-fast: false
matrix:
folders: ${{ fromJson(needs.setup.outputs.quantization_matrix) }}
machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
machine_type: [aws-g4dn-2xlarge-cache]
runs-on:
group: '${{ matrix.machine_type }}'
container:
Expand Down Expand Up @@ -495,80 +495,3 @@ jobs:
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

run_extract_warnings:
# Let's only do this for the job `run_models_gpu` to simplify the (already complex) logic.
if: ${{ always() && inputs.job == 'run_models_gpu' }}
name: Extract warnings in CI artifacts
runs-on: ubuntu-22.04
needs: [setup, run_models_gpu]
steps:
- name: Checkout transformers
uses: actions/checkout@v4
with:
fetch-depth: 2

- name: Install transformers
run: pip install transformers

- name: Show installed libraries and their versions
run: pip freeze

- name: Create output directory
run: mkdir warnings_in_ci

- uses: actions/download-artifact@v4
with:
path: warnings_in_ci

- name: Show artifacts
run: echo "$(python3 -c 'import os; d = os.listdir(); print(d)')"
working-directory: warnings_in_ci

- name: Extract warnings in CI artifacts
run: |
python3 utils/extract_warnings.py --workflow_run_id ${{ github.run_id }} --output_dir warnings_in_ci --token ${{ secrets.ACCESS_REPO_INFO_TOKEN }} --from_gh
echo "$(python3 -c 'import os; import json; fp = open("warnings_in_ci/selected_warnings.json"); d = json.load(fp); d = "\n".join(d) ;print(d)')"
- name: Upload artifact
if: ${{ always() }}
uses: actions/upload-artifact@v4
with:
name: warnings_in_ci
path: warnings_in_ci/selected_warnings.json

send_results:
name: Slack Report
needs: [
setup,
run_models_gpu,
run_pipelines_torch_gpu,
run_pipelines_tf_gpu,
run_examples_gpu,
run_torch_cuda_extensions_gpu,
run_quantization_torch_gpu,
run_extract_warnings
]
if: ${{ always() }}
uses: ./.github/workflows/slack-report.yml
with:
job: ${{ inputs.job }}
# This would be `skipped` if `setup` is skipped.
setup_status: ${{ needs.setup.result }}
slack_report_channel: ${{ inputs.slack_report_channel }}
# This would be an empty string if `setup` is skipped.
folder_slices: ${{ needs.setup.outputs.folder_slices }}
quantization_matrix: ${{ needs.setup.outputs.quantization_matrix }}
ci_event: ${{ inputs.ci_event }}

secrets: inherit

check_new_model_failures:
if: ${{ always() && inputs.ci_event == 'Daily CI' && inputs.job == 'run_models_gpu' && needs.send_results.result == 'success' }}
name: Check new model failures
needs: send_results
uses: ./.github/workflows/check_failed_model_tests.yml
with:
docker: ${{ inputs.docker }}
start_sha: ${{ github.sha }}
secrets: inherit
1 change: 1 addition & 0 deletions utils/split_model_tests.py
Original file line number Diff line number Diff line change
Expand Up @@ -62,4 +62,5 @@
start = end
end = start + num_jobs_per_splits + (1 if idx < num_jobs % args.num_splits else 0)
model_splits.append(d[start:end])
model_splits = [["models/vit"]]
print(model_splits)

0 comments on commit c26cede

Please sign in to comment.