Merge pull request #174 from GATEOverflow/dev

Bert is now edge only

Author: arjunsuresh

.github/workflows/test-mlperf-inference-mixtral.yml

@@ -1,11 +1,8 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
-
 name: MLPerf inference MIXTRAL-8x7B
 
 on:
   schedule:
-    - cron: "59 19 * * *"   # 30th minute and 20th hour => 20:30 UTC => 2 AM IST 
+    - cron: "59 23 * * */5"   # 30th minute and 20th hour => 20:30 UTC => 2 AM IST 
 
 jobs:
   build_reference:

.github/workflows/test-nvidia-mlperf-inference-implementations.yml

@@ -43,6 +43,11 @@ jobs:
             gpu_name=rtx_4090
             docker_string=" --docker"
           fi
+          if [ "${{ matrix.model }}" = "bert-99" ] || [ "${{ matrix.model }}" = "bert-99.9" ]; then
+            category="edge"
+          else
+            category="datacenter,edge"
+          fi
 
           if [ -f "gh_action/bin/deactivate" ]; then source gh_action/bin/deactivate; fi
           python3 -m venv gh_action
@@ -51,6 +56,6 @@ jobs:
           pip install --upgrade mlcflow
           mlc pull repo mlcommons@mlperf-automations --branch=dev
           
-          mlcr --tags=run-mlperf,inference,_all-scenarios,_submission,_full,_r5.0-dev --preprocess_submission=yes --pull_changes=yes --pull_inference_changes=yes --execution_mode=valid --gpu_name=$gpu_name --pull_changes=yes --pull_inference_changes=yes --model=${{ matrix.model }} --submitter="MLCommons" --hw_name=$hw_name --implementation=nvidia --backend=tensorrt --category=datacenter,edge --division=closed  --docker_dt --docker_mlc_repo=mlcommons@mlperf-automations --docker_mlc_repo_branch=dev --adr.compiler.tags=gcc --device=cuda --use_model_from_host=yes --use_dataset_from_host=yes --results_dir=$HOME/gh_action_results --submission_dir=$HOME/gh_action_submissions --clean  $docker_string --quiet
+          mlcr --tags=run-mlperf,inference,_all-scenarios,_submission,_full,_r5.0-dev --preprocess_submission=yes --pull_changes=yes --pull_inference_changes=yes --execution_mode=valid --gpu_name=$gpu_name --pull_changes=yes --pull_inference_changes=yes --model=${{ matrix.model }} --submitter="MLCommons" --hw_name=$hw_name --implementation=nvidia --backend=tensorrt --category=$category --division=closed  --docker_dt --docker_mlc_repo=mlcommons@mlperf-automations --docker_mlc_repo_branch=dev --adr.compiler.tags=gcc --device=cuda --use_model_from_host=yes --use_dataset_from_host=yes --results_dir=$HOME/gh_action_results --submission_dir=$HOME/gh_action_submissions --clean  $docker_string --quiet
 
           mlcr --tags=push,github,mlperf,inference,submission --repo_url=https://github.com/mlcommons/mlperf_inference_unofficial_submissions_v5.0 --repo_branch=auto-update --commit_message="Results from GH action on NVIDIA_$hw_name" --quiet --submission_dir=$HOME/gh_action_submissions --hw_name=$hw_name