[Nova] GHA Linux GPU Job (#6804)

* [Nova] GHA Linux GPU Job

* increase timeout since jobs timeout and cancel after 30 mins

* bigger instance and longer timeout

* use instance with more gpu memory and only run py38 and cu116 on PR CI

Author: osalpekar

.github/workflows/test-linux-cpu.yml

@@ -16,7 +16,7 @@ jobs:
   tests:
     strategy:
       matrix:
-        py_vers: ["3.7", "3.8", "3.9", "3.10"]
+        python_version: ["3.7", "3.8", "3.9", "3.10"]
       fail-fast: false
     uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     with:
@@ -27,7 +27,7 @@ jobs:
         git config --global --add safe.directory /__w/vision/vision
 
         # Set up Environment Variables
-        export PYTHON_VERSION="${{ matrix.py_vers }}"
+        export PYTHON_VERSION="${{ matrix.python_version }}"
         export VERSION="cpu"
         export CUDATOOLKIT="cpuonly"
 

.github/workflows/test-linux-gpu.yml

@@ -0,0 +1,61 @@
+name: Unit-tests on Linux GPU
+
+on:
+  pull_request:
+  push:
+    branches:
+      - nightly
+      - main
+      - release/*
+  workflow_dispatch:
+
+env:
+  CHANNEL: "nightly"
+
+jobs:
+  tests:
+    strategy:
+      matrix:
+        python_version: ["3.8"]
+        cuda_arch_version: ["11.6"]
+      fail-fast: false
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    with:
+      runner: linux.g5.4xlarge.nvidia.gpu
+      repository: pytorch/vision
+      gpu-arch-type: cuda
+      gpu-arch-version: ${{ matrix.cuda_arch_version }}
+      timeout: 120
+      script: |
+        # Mark Build Directory Safe
+        git config --global --add safe.directory /__w/vision/vision
+
+        # Set up Environment Variables
+        export PYTHON_VERSION="${{ matrix.python_version }}"
+        export VERSION="${{ matrix.cuda_arch_version }}"
+        export CUDATOOLKIT="pytorch-cuda=${VERSION}"
+
+        # Set CHANNEL
+        if [[ (${GITHUB_EVENT_NAME} = 'pull_request' && (${GITHUB_BASE_REF} = 'release'*)) || (${GITHUB_REF} = 'refs/heads/release'*) ]]; then
+          export CHANNEL=test
+        else
+          export CHANNEL=nightly
+        fi
+
+        # Create Conda Env
+        conda create -yp ci_env python="${PYTHON_VERSION}" numpy libpng jpeg scipy
+        conda activate /work/ci_env
+        
+        # Install PyTorch, Torchvision, and testing libraries
+        set -ex
+        conda install \
+          --yes \
+          -c "pytorch-${CHANNEL}" \
+          -c nvidia "pytorch-${CHANNEL}"::pytorch[build="*${VERSION}*"] \
+          "${CUDATOOLKIT}"
+        python3 setup.py develop
+        python3 -m pip install pytest pytest-mock 'av<10'
+
+        # Run Tests
+        python3 -m torch.utils.collect_env
+        python3 -m pytest --junitxml=test-results/junit.xml -v --durations 20