revert partially Enable/Optimize flan t5 xxl on deepspeed z3 #257 #696
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: Unit and integration tests | |
# WARNING: As this workflow supports the pull_request_target event, please exercise extra care when editing it. | |
# Reference: https://gist.github.com/fxmarty/fba1ea3b2ebbf9a75cca71c08f05a85b | |
on: | |
workflow_dispatch: | |
pull_request_target: | |
branches: [ main ] | |
paths: | |
- "optimum/**.py" | |
- "tests/**.py" | |
- "setup.py" | |
concurrency: | |
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }} | |
cancel-in-progress: true | |
jobs: | |
authorize: | |
environment: | |
${{ github.event_name == 'pull_request_target' && | |
github.event.pull_request.head.repo.full_name != github.repository && | |
'external' || 'internal' }} | |
runs-on: ubuntu-latest | |
steps: | |
- run: true | |
start-runner: | |
name: Start self-hosted EC2 runner | |
needs: authorize | |
runs-on: ubuntu-20.04 | |
env: | |
AWS_REGION: us-east-1 | |
EC2_AMI_ID: ami-0ed6a6bdb94a8de33 | |
EC2_INSTANCE_TYPE: dl1.24xlarge | |
EC2_SUBNET_ID: subnet-b7533b96 | |
EC2_SECURITY_GROUP: sg-059956d687c7ec5c2 | |
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: ${{ env.EC2_SECURITY_GROUP }} | |
aws-resource-tags: > # optional, requires additional permissions | |
[ | |
{"Key": "Name", "Value": "optimum-habana-ci-fast-tests"}, | |
{"Key": "GitHubRepository", "Value": "${{ github.repository }}"} | |
] | |
transformers: | |
name: Run tests for optimum.habana.transformers | |
needs: | |
- authorize | |
- 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 | |
env: | |
AWS_REGION: us-east-1 | |
steps: | |
- name: Checkout on branch | |
if: github.event_name != 'pull_request_target' | |
uses: actions/checkout@v2 | |
with: | |
ref: ${{ github.ref }} | |
- name: Checkout on PR merge commit | |
if: github.event_name == 'pull_request_target' | |
uses: actions/checkout@v2 | |
with: | |
ref: "refs/pull/${{ github.event.number }}/merge" | |
fetch-depth: 2 | |
- name: Security - check PR SHA | |
if: github.event_name == 'pull_request_target' | |
run: | | |
[[ "$(git rev-parse 'HEAD^2')" == "${{ github.event.pull_request.head.sha }}" ]] | |
- name: Pull image | |
run: | | |
docker pull vault.habana.ai/gaudi-docker/1.10.0/ubuntu20.04/habanalabs/pytorch-installer-2.0.1:latest | |
- name: Run tests | |
run: | | |
docker run \ | |
-v $PWD:/root/workspace \ | |
--workdir=/root/workspace \ | |
--runtime=habana \ | |
-e HABANA_VISIBLE_DEVICES=all \ | |
-e OMPI_MCA_btl_vader_single_copy_mechanism=none \ | |
--cap-add=sys_nice \ | |
--net=host \ | |
--ipc=host \ | |
vault.habana.ai/gaudi-docker/1.10.0/ubuntu20.04/habanalabs/pytorch-installer-2.0.1:latest \ | |
/bin/bash tests/ci/fast_tests.sh | |
diffusers: | |
name: Run tests for optimum.habana.diffusers | |
needs: | |
- authorize | |
- start-runner # required to get output from the start-runner job | |
- transformers # required to wait for the previous tests to finish | |
runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner | |
env: | |
AWS_REGION: us-east-1 | |
steps: | |
- name: Checkout on branch | |
if: github.event_name != 'pull_request_target' | |
uses: actions/checkout@v2 | |
with: | |
ref: ${{ github.ref }} | |
- name: Checkout on PR merge commit | |
if: github.event_name == 'pull_request_target' | |
uses: actions/checkout@v2 | |
with: | |
ref: "refs/pull/${{ github.event.number }}/merge" | |
fetch-depth: 2 | |
- name: Security - check PR SHA | |
if: github.event_name == 'pull_request_target' | |
run: | | |
[[ "$(git rev-parse 'HEAD^2')" == "${{ github.event.pull_request.head.sha }}" ]] | |
- name: Pull image | |
run: | | |
docker pull vault.habana.ai/gaudi-docker/1.10.0/ubuntu20.04/habanalabs/pytorch-installer-2.0.1:latest | |
- name: Run tests | |
run: | | |
docker run \ | |
-v $PWD:/root/workspace \ | |
--workdir=/root/workspace \ | |
--runtime=habana \ | |
-e HABANA_VISIBLE_DEVICES=all \ | |
-e OMPI_MCA_btl_vader_single_copy_mechanism=none \ | |
--cap-add=sys_nice \ | |
--net=host \ | |
--ipc=host \ | |
vault.habana.ai/gaudi-docker/1.10.0/ubuntu20.04/habanalabs/pytorch-installer-2.0.1:latest \ | |
/bin/bash tests/ci/fast_tests_diffusers.sh | |
stop-runner: | |
name: Stop self-hosted EC2 runner | |
needs: | |
- authorize | |
- start-runner # required to get output from the start-runner job | |
- transformers # required to wait for the tests to be finished | |
- diffusers # required to wait for the tests to be finished | |
runs-on: ubuntu-20.04 | |
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 }} |