From b262224516c359172d134b307c557c72bc2507f0 Mon Sep 17 00:00:00 2001
From: Guillaume LEGENDRE <glegendre01@gmail.com>
Date: Tue, 13 Feb 2024 13:18:01 +0100
Subject: [PATCH] Move GPU to EKS

---
 .github/workflows/gpu-integ-test.yaml | 67 +--------------------------
 1 file changed, 2 insertions(+), 65 deletions(-)

diff --git a/.github/workflows/gpu-integ-test.yaml b/.github/workflows/gpu-integ-test.yaml
index ede153ea..e85f5498 100644
--- a/.github/workflows/gpu-integ-test.yaml
+++ b/.github/workflows/gpu-integ-test.yaml
@@ -13,45 +13,8 @@ concurrency:
 
 
 jobs:
-  start-runner:
-    name: Start self-hosted EC2 runner
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: us-east-1
-      EC2_AMI_ID: ami-0dc1c26161f869ed1
-      EC2_INSTANCE_TYPE: g4dn.xlarge
-      EC2_SUBNET_ID: subnet-859322b4,subnet-b7533b96,subnet-47cfad21,subnet-a396b2ad,subnet-06576a4b,subnet-df0f6180
-      EC2_SECURITY_GROUP: sg-0bb210cd3ec725a13
-      EC2_IAM_ROLE: optimum-ec2-github-actions-role
-    outputs:
-      label: ${{ steps.start-ec2-runner.outputs.label }}
-      ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Start EC2 runner
-        id: start-ec2-runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: start
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          ec2-image-id: ${{ env.EC2_AMI_ID }}
-          ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
-          subnet-id: ${{ env.EC2_SUBNET_ID }}
-          security-group-id: ${{ env.EC2_SECURITY_GROUP }}
-          iam-role-name: ${{ env.EC2_IAM_ROLE }}
-          aws-resource-tags: > # optional, requires additional permissions
-            [
-              {"Key": "Name", "Value": "ec2-optimum-github-runner"},
-              {"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
-            ]
   pytorch-integration-test:
-    needs: start-runner # required to start the main job when the runner is ready
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     env:
       AWS_REGION: us-east-1
     steps:
@@ -69,9 +32,8 @@ jobs:
         run: RUN_SLOW=True make integ-test
   tensorflow-integration-test:
     needs:
-      - start-runner
       - pytorch-integration-test
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     env:
       AWS_REGION: us-east-1
     steps:
@@ -89,28 +51,3 @@ jobs:
         run: docker build -t starlette-transformers:gpu -f dockerfiles/tensorflow/gpu/Dockerfile .
       - name: Run Integration Tests
         run: RUN_SLOW=True make integ-test
-
-  stop-runner:
-    name: Stop self-hosted EC2 runner
-    needs:
-      - start-runner
-      - pytorch-integration-test
-      - tensorflow-integration-test
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: us-east-1
-    if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Stop EC2 runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: stop
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          label: ${{ needs.start-runner.outputs.label }}
-          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }} 
\ No newline at end of file