Use A100 for LLama2 model test (#21068)

### Description




### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

Author: mszhanyi

tools/ci_build/github/azure-pipelines/bigmodels-ci-pipeline.yml

@@ -296,7 +296,10 @@ stages:
       skipComponentGovernanceDetection: true
     workspace:
       clean: all
-    pool: Onnxruntime-Linux-A10-24G
+    pool:
+      name: Onnxruntime-Linux-GPU-A100-WUS3
+      demands:
+      - WorkFolder -equals /mnt/storage/
     steps:
     - task: mspremier.PostBuildCleanup.PostBuildCleanup-task.PostBuildCleanup@3
       displayName: 'Clean Agent Directories'