added gh actions - nvidia implementation

.github/workflows/test-all-nvidia-mlperf-implementation.yml

@@ -0,0 +1,27 @@
+name: MLPerf inference Nvidia implementations
+
+on:
+  schedule:
+    - cron: "30 14 * * *" #to be adjusted
+
+build_nvidia:
+      if: github.repository_owner == 'anandhu-eng'
+      runs-on: [ self-hosted, linux, x64, GO-i9]
+      strategy:
+        fail-fast: false
+        matrix:
+          python-version: [ "3.12" ]
+          model: [ "resnet50", "3d-unet-99", "3d-unet-99.9", "bert-99", "bert-99.9", "retinanet" ]
+      steps:
+      - name: Preprocessing step for the run
+        run: |
+          if [ -f "gh_action/bin/deactivate" ]; then source gh_action/bin/deactivate; fi
+          python3 -m venv gh_action
+          source gh_action/bin/activate
+          export CM_REPOS=$HOME/GH_CM
+          pip install --upgrade cm4mlops
+          cm pull repo
+      - name: Test MLPerf Inference NVIDIA ${{ matrix.model }}
+        run: |
+          cm run script --tags=run-mlperf,inference,_submission,_r4.1-dev,_short --submitter="MLCommons" --hw_name=gh_ubuntu_x86  --model=${{ matrix.model }}  --implementation=nvidia    --backend=tensorrt    --category=datacenter    --scenario=Offline --test_query_count=500 --target_qps=1 --docker_dt=yes --docker_it=no --docker_cm_repo=gateoverflow@cm4mlops --adr.compiler.tags=gcc --device=cuda --results_dir=$HOME/gh_action_results --submission_dir=$HOME/gh_action_submissions --clean  --docker --quiet
+          cm run script --tags=push,github,mlperf,inference,submission --repo_url=https://github.com/gateoverflow/mlperf_inference_test_submissions_v5.0 --repo_branch=main --commit_message="Results from ${{ matrix.model }} GH action on NVIDIARTX4090" --quiet --submission_dir=$HOME/gh_action_submissions