remove test runners

remove update hf cli
update huggingface cli
2025-10-21 01:23:56 +08:00 · 2024-09-16 10:22:00 +02:00 · 2024-09-16 10:18:03 +02:00 · 2024-09-04 10:04:37 +02:00 · 2024-09-03 17:16:33 +02:00 · 2024-09-02 17:41:10 +02:00
2 changed files with 24 additions and 17 deletions
--- a/.github/workflows/model_jobs.yml
+++ b/.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/
@ -82,8 +83,8 @@ jobs:
        if: ${{ contains(inputs.docker, '-past-') && contains(inputs.docker, '-pytorch-') }}
        working-directory: /transformers
        run: |
-          python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate
-
+          python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate\
+          
      - name: NVIDIA-SMI
        run: |
          nvidia-smi
@ -100,7 +101,7 @@ jobs:
      - name: Run all tests on GPU
        working-directory: /transformers
        run: python3 -m pytest -rsfE -v --make-reports=${{ inputs.machine_type }}_run_models_gpu_${{ matrix.folders }}_test_reports tests/${{ matrix.folders }}
-
+        
      - name: Failure short reports
        if: ${{ failure() }}
        continue-on-error: true
--- a/.github/workflows/self-scheduled.yml
+++ b/.github/workflows/self-scheduled.yml
@ -50,8 +50,9 @@ jobs:
    name: Setup
    strategy:
      matrix:
-        machine_type: [single-gpu, multi-gpu]
-    runs-on: ['${{ matrix.machine_type }}', nvidia-gpu, t4, '${{ inputs.runner }}']
+        machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
+    runs-on: 
+      group: '${{ matrix.machine_type }}'
    container:
      image: huggingface/transformers-all-latest-gpu
      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
@ -102,7 +103,7 @@ jobs:
    strategy:
      fail-fast: false
      matrix:
-        machine_type: [single-gpu, multi-gpu]
+        machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
        slice_id: ${{ fromJSON(needs.setup.outputs.slice_ids) }}
    uses: ./.github/workflows/model_jobs.yml
    with:
@ -119,8 +120,9 @@ jobs:
    strategy:
      fail-fast: false
      matrix:
-        machine_type: [single-gpu, multi-gpu]
-    runs-on: ['${{ matrix.machine_type }}', nvidia-gpu, t4, '${{ inputs.runner }}']
+        machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
+    runs-on: 
+      group: '${{ matrix.machine_type }}'
    container:
      image: huggingface/transformers-pytorch-gpu
      options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
@ -169,8 +171,9 @@ jobs:
    strategy:
      fail-fast: false
      matrix:
-        machine_type: [single-gpu, multi-gpu]
-    runs-on: ['${{ matrix.machine_type }}', nvidia-gpu, t4, '${{ inputs.runner }}']
+        machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
+    runs-on: 
+      group: '${{ matrix.machine_type }}'
    container:
      image: huggingface/transformers-tensorflow-gpu
      options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
@ -220,8 +223,9 @@ jobs:
    strategy:
      fail-fast: false
      matrix:
-        machine_type: [single-gpu]
-    runs-on: ['${{ matrix.machine_type }}', nvidia-gpu, t4, '${{ inputs.runner }}']
+        machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
+    runs-on: 
+      group: '${{ matrix.machine_type }}'
    container:
      image: huggingface/transformers-all-latest-gpu
      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
@ -271,8 +275,9 @@ jobs:
    strategy:
      fail-fast: false
      matrix:
-        machine_type: [single-gpu, multi-gpu]
-    runs-on: ['${{ matrix.machine_type }}', nvidia-gpu, t4, '${{ inputs.runner }}']
+        machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
+    runs-on: 
+      group: '${{ matrix.machine_type }}'
    container:
      image: ${{ inputs.docker }}
      options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
@ -352,8 +357,9 @@ jobs:
      fail-fast: false
      matrix:
        folders: ${{ fromJson(needs.setup.outputs.quantization_matrix) }}
-        machine_type: [single-gpu, multi-gpu]
-    runs-on: ['${{ matrix.machine_type }}', nvidia-gpu, t4, '${{ inputs.runner }}']
+        machine_type: [aws-g4dn-2xlarge-cache, aws-g4dn-12xlarge-cache]
+    runs-on: 
+      group: '${{ 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/
Author	SHA1	Message	Date
Guillaume LEGENDRE	725208e076	remove test runners	2024-09-16 10:22:00 +02:00
Guillaume LEGENDRE	a7e7c7519f	remove update hf cli	2024-09-16 10:18:03 +02:00
Guillaume LEGENDRE	9972078bb4	update huggingface cli	2024-09-04 10:04:37 +02:00
Guillaume LEGENDRE	ab83a43549	remove debug	2024-09-03 17:16:33 +02:00
Guillaume LEGENDRE	bc7ec7a102	add debug	2024-09-02 17:41:10 +02:00
Guillaume LEGENDRE	98b236baad	remove debug	2024-09-02 15:00:57 +02:00
Guillaume LEGENDRE	78acbf3ddb	test others S3 options	2024-09-02 14:30:59 +02:00
Guillaume LEGENDRE	5ac1b33896	test debug	2024-08-20 17:28:41 +02:00
Guillaume LEGENDRE	badf318907	test new runner cache	2024-08-12 16:23:12 +02:00