Merge branch 'main' into compressed-tensors-quantizer

.circleci/config.yml

@@ -47,13 +47,13 @@ jobs:
 
             - run:
                 name: "Retrieve Artifact Paths"
-                env:
-                    CIRCLE_TOKEN: ${{ secrets.CI_ARTIFACT_TOKEN }}
+                # [reference] https://circleci.com/docs/api/v2/index.html#operation/getJobArtifacts
+                # `CIRCLE_TOKEN` is defined as an environment variables set within a context, see `https://circleci.com/docs/contexts/`
                 command: |
                     project_slug="gh/${CIRCLE_PROJECT_USERNAME}/${CIRCLE_PROJECT_REPONAME}"
                     job_number=${CIRCLE_BUILD_NUM}
                     url="https://circleci.com/api/v2/project/${project_slug}/${job_number}/artifacts"
-                    curl -o  test_preparation/artifacts.json ${url}
+                    curl -o test_preparation/artifacts.json ${url} --header "Circle-Token: $CIRCLE_TOKEN"
             - run:
                 name: "Prepare pipeline parameters"
                 command: |
@@ -82,22 +82,49 @@ jobs:
         parallelism: 1
         steps:
             - checkout
-            - run: uv pip install -e .
-            - run: |
-                  mkdir test_preparation
-                  echo -n "tests" > test_preparation/test_list.txt
-                  echo -n "all" > test_preparation/examples_test_list.txt
-                  echo -n "tests/repo_utils" > test_preparation/test_repo_utils.txt
+            - run: uv pip install -U -e .
+            - run: echo 'export "GIT_COMMIT_MESSAGE=$(git show -s --format=%s)"' >> "$BASH_ENV" && source "$BASH_ENV"
+            - run: mkdir -p test_preparation
+            - run: python utils/tests_fetcher.py --fetch_all | tee tests_fetched_summary.txt
+            - run: python utils/tests_fetcher.py --filter_tests
+            - run: export "GIT_COMMIT_MESSAGE=$(git show -s --format=%s)" && echo $GIT_COMMIT_MESSAGE && python .circleci/create_circleci_config.py --fetcher_folder test_preparation
             - run: |
-                  echo -n "tests" > test_list.txt
-                  python utils/tests_fetcher.py --filter_tests
-                  mv test_list.txt test_preparation/filtered_test_list.txt
-            - run: python .circleci/create_circleci_config.py --fetcher_folder test_preparation
-            - run: cp test_preparation/generated_config.yml test_preparation/generated_config.txt
+                if [ ! -s test_preparation/generated_config.yml ]; then
+                    echo "No tests to run, exiting early!"
+                    circleci-agent step halt
+                fi
+
+            - store_artifacts:
+                path: test_preparation
+
+            - run:
+                name: "Retrieve Artifact Paths"
+                env:
+                    CIRCLE_TOKEN: ${{ secrets.CI_ARTIFACT_TOKEN }}
+                command: |
+                    project_slug="gh/${CIRCLE_PROJECT_USERNAME}/${CIRCLE_PROJECT_REPONAME}"
+                    job_number=${CIRCLE_BUILD_NUM}
+                    url="https://circleci.com/api/v2/project/${project_slug}/${job_number}/artifacts"
+                    curl -o  test_preparation/artifacts.json ${url}
+            - run:
+                name: "Prepare pipeline parameters"
+                command: |
+                    python utils/process_test_artifacts.py 
+
+            # To avoid too long generated_config.yaml on the continuation orb, we pass the links to the artifacts as parameters.
+            # Otherwise the list of tests was just too big. Explicit is good but for that it was a limitation.
+            # We used:
+
+            # https://circleci.com/docs/api/v2/index.html#operation/getJobArtifacts : to get the job artifacts
+            # We could not pass a nested dict, which is why we create the test_file_... parameters for every single job
+
             - store_artifacts:
-                  path: test_preparation/generated_config.txt
+                path: test_preparation/transformed_artifacts.json
+            - store_artifacts:
+                path: test_preparation/artifacts.json
             - continuation/continue:
-                  configuration_path: test_preparation/generated_config.yml
+                parameters:  test_preparation/transformed_artifacts.json
+                configuration_path: test_preparation/generated_config.yml
 
     check_code_quality:
         working_directory: ~/transformers
@@ -163,7 +190,10 @@ workflows:
             - check_circleci_user
             - check_code_quality
             - check_repository_consistency
-            - fetch_tests
+            - fetch_tests:
+                # [reference] https://circleci.com/docs/contexts/
+                context:
+                    - TRANSFORMERS_CONTEXT
 
     nightly:
         when: <<pipeline.parameters.nightly>>

.circleci/create_circleci_config.py

@@ -312,6 +312,15 @@ def job_name(self):
 )
 
 
+non_model_job = CircleCIJob(
+    "non_model",
+    docker_image=[{"image": "huggingface/transformers-torch-light"}],
+    marker="not generate",
+    parallelism=6,
+    pytest_num_workers=8,
+)
+
+
 # We also include a `dummy.py` file in the files to be doc-tested to prevent edge case failure. Otherwise, the pytest
 # hangs forever during test collection while showing `collecting 0 items / 21 errors`. (To see this, we have to remove
 # the bash output redirection.)
@@ -336,7 +345,7 @@ def job_name(self):
     pytest_num_workers=1,
 )
 
-REGULAR_TESTS = [torch_and_tf_job, torch_and_flax_job, torch_job, tf_job, flax_job, hub_job, onnx_job, tokenization_job, processor_job, generate_job] # fmt: skip
+REGULAR_TESTS = [torch_and_tf_job, torch_and_flax_job, torch_job, tf_job, flax_job, hub_job, onnx_job, tokenization_job, processor_job, generate_job, non_model_job] # fmt: skip
 EXAMPLES_TESTS = [examples_torch_job, examples_tensorflow_job]
 PIPELINE_TESTS = [pipelines_torch_job, pipelines_tf_job]
 REPO_UTIL_TESTS = [repo_utils_job]

.github/workflows/build_documentation.yml

@@ -1,6 +1,7 @@
 name: Build documentation
 
 on:
+  workflow_dispatch:
   push:
     branches:
       - main

.github/workflows/model_jobs.yml

@@ -41,7 +41,8 @@ jobs:
       fail-fast: false
       matrix:
         folders: ${{ fromJson(inputs.folder_slices)[inputs.slice_id] }}
-    runs-on: ['${{ inputs.machine_type }}', nvidia-gpu, t4, '${{ inputs.runner }}']
+    runs-on:
+      group: '${{ inputs.machine_type }}'
     container:
       image: ${{ inputs.docker }}
       options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
@@ -97,25 +98,42 @@ jobs:
         working-directory: /transformers
         run: pip freeze
 
+      - name: Set `machine_type` for report and artifact names
+        working-directory: /transformers
+        shell: bash
+        run: |
+          echo "${{ inputs.machine_type }}"
+
+          if [ "${{ inputs.machine_type }}" = "aws-g4dn-2xlarge-cache" ]; then
+            machine_type=single-gpu
+          elif [ "${{ inputs.machine_type }}" = "aws-g4dn-12xlarge-cache" ]; then
+            machine_type=multi-gpu
+          else
+            machine_type=${{ inputs.machine_type }}
+          fi
+
+          echo "$machine_type"
+          echo "machine_type=$machine_type" >> $GITHUB_ENV
+
       - name: Run all tests on GPU
         working-directory: /transformers
-        run: python3 -m pytest -rsfE -v --make-reports=${{ inputs.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports tests/${{ matrix.folders }}
+        run: python3 -m pytest -rsfE -v --make-reports=${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports tests/${{ matrix.folders }}
 
       - name: Failure short reports
         if: ${{ failure() }}
         continue-on-error: true
-        run: cat /transformers/reports/${{ inputs.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports/failures_short.txt
+        run: cat /transformers/reports/${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports/failures_short.txt
 
       - name: Run test
         shell: bash
         run: |
-          mkdir -p /transformers/reports/${{ inputs.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports
-          echo "hello" > /transformers/reports/${{ inputs.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports/hello.txt
-          echo "${{ inputs.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports"
+          mkdir -p /transformers/reports/${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports
+          echo "hello" > /transformers/reports/${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports/hello.txt
+          echo "${{ env.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports"
 
-      - name: "Test suite reports artifacts: ${{ inputs.machine_type }}_run_models_gpu_${{ env.matrix_folders }}_test_reports"
+      - name: "Test suite reports artifacts: ${{ env.machine_type }}_run_models_gpu_${{ env.matrix_folders }}_test_reports"
         if: ${{ always() }}
         uses: actions/upload-artifact@v4
         with:
-          name: ${{ inputs.machine_type }}_run_models_gpu_${{ env.matrix_folders }}_test_reports
-          path: /transformers/reports/${{ inputs.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports
+          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

.github/workflows/self-scheduled-caller.yml

@@ -2,6 +2,9 @@ name: Self-hosted runner (scheduled)
 
 
 on:
+  repository_dispatch:
+  schedule:
+    - cron: "17 2 * * *"
   push:
     branches:
       - run_scheduled_ci*