mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-06 12:20:52 +01:00
[ci] do not run distributed jobs for windows (#73064)
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/73064 These accidentally got turned on by https://github.com/pytorch/pytorch/pull/73001. Turn them off. Test Plan: Imported from OSS Reviewed By: shannonzhu Differential Revision: D34332530 Pulled By: suo fbshipit-source-id: a6493b7d94465fa9141f1527648dbbec09c5706d
This commit is contained in:
parent
2f8f5e4971
commit
b18c95e4a6
4
.github/scripts/generate_ci_workflows.py
vendored
4
.github/scripts/generate_ci_workflows.py
vendored
|
|
@ -385,6 +385,7 @@ WINDOWS_WORKFLOWS = [
|
||||||
arch="windows",
|
arch="windows",
|
||||||
build_environment="win-vs2019-cpu-py3",
|
build_environment="win-vs2019-cpu-py3",
|
||||||
cuda_version="cpu",
|
cuda_version="cpu",
|
||||||
|
enable_distributed_test=False,
|
||||||
test_runner_type=WINDOWS_CPU_TEST_RUNNER,
|
test_runner_type=WINDOWS_CPU_TEST_RUNNER,
|
||||||
num_test_shards=2,
|
num_test_shards=2,
|
||||||
ciflow_config=CIFlowConfig(
|
ciflow_config=CIFlowConfig(
|
||||||
|
|
@ -396,6 +397,7 @@ WINDOWS_WORKFLOWS = [
|
||||||
arch="windows",
|
arch="windows",
|
||||||
build_environment="win-vs2019-cuda11.3-py3",
|
build_environment="win-vs2019-cuda11.3-py3",
|
||||||
cuda_version="11.3",
|
cuda_version="11.3",
|
||||||
|
enable_distributed_test=False,
|
||||||
test_runner_type=WINDOWS_CUDA_TEST_RUNNER,
|
test_runner_type=WINDOWS_CUDA_TEST_RUNNER,
|
||||||
num_test_shards=2,
|
num_test_shards=2,
|
||||||
enable_force_on_cpu_test=True,
|
enable_force_on_cpu_test=True,
|
||||||
|
|
@ -408,6 +410,7 @@ WINDOWS_WORKFLOWS = [
|
||||||
arch="windows",
|
arch="windows",
|
||||||
build_environment="periodic-win-vs2019-cuda11.5-py3",
|
build_environment="periodic-win-vs2019-cuda11.5-py3",
|
||||||
cuda_version="11.5",
|
cuda_version="11.5",
|
||||||
|
enable_distributed_test=False,
|
||||||
test_runner_type=WINDOWS_CUDA_TEST_RUNNER,
|
test_runner_type=WINDOWS_CUDA_TEST_RUNNER,
|
||||||
num_test_shards=2,
|
num_test_shards=2,
|
||||||
enable_force_on_cpu_test=True,
|
enable_force_on_cpu_test=True,
|
||||||
|
|
@ -421,6 +424,7 @@ WINDOWS_WORKFLOWS = [
|
||||||
arch="windows",
|
arch="windows",
|
||||||
build_environment="periodic-win-vs2019-cuda11.1-py3",
|
build_environment="periodic-win-vs2019-cuda11.1-py3",
|
||||||
cuda_version="11.1",
|
cuda_version="11.1",
|
||||||
|
enable_distributed_test=False,
|
||||||
test_runner_type=WINDOWS_CUDA_TEST_RUNNER,
|
test_runner_type=WINDOWS_CUDA_TEST_RUNNER,
|
||||||
num_test_shards=2,
|
num_test_shards=2,
|
||||||
is_scheduled="45 0,4,8,12,16,20 * * *",
|
is_scheduled="45 0,4,8,12,16,20 * * *",
|
||||||
|
|
|
||||||
156
.github/workflows/generated-periodic-win-vs2019-cuda11.1-py3.yml
generated
vendored
156
.github/workflows/generated-periodic-win-vs2019-cuda11.1-py3.yml
generated
vendored
|
|
@ -131,162 +131,6 @@ jobs:
|
||||||
run: |
|
run: |
|
||||||
rm -rf "${PYTORCH_FINAL_PACKAGE_DIR}"
|
rm -rf "${PYTORCH_FINAL_PACKAGE_DIR}"
|
||||||
rm -rf ./*
|
rm -rf ./*
|
||||||
test_distributed_1_1:
|
|
||||||
name: test (distributed, 1, 1, windows.8xlarge.nvidia.gpu)
|
|
||||||
timeout-minutes: 240
|
|
||||||
env:
|
|
||||||
JOB_BASE_NAME: periodic-win-vs2019-cuda11.1-py3-test
|
|
||||||
SHARD_NUMBER: 1
|
|
||||||
NUM_TEST_SHARDS: 1
|
|
||||||
TEST_CONFIG: distributed
|
|
||||||
http_proxy: "http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128"
|
|
||||||
https_proxy: "http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128"
|
|
||||||
PR_BODY: ${{ github.event.pull_request.body }}
|
|
||||||
needs: build
|
|
||||||
runs-on: windows.8xlarge.nvidia.gpu
|
|
||||||
steps:
|
|
||||||
- name: Display EC2 information
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
set -euo pipefail
|
|
||||||
function get_ec2_metadata() {
|
|
||||||
# Pulled from instance metadata endpoint for EC2
|
|
||||||
# see https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/instancedata-data-retrieval.html
|
|
||||||
category=$1
|
|
||||||
curl -fsSL "http://169.254.169.254/latest/meta-data/${category}"
|
|
||||||
}
|
|
||||||
echo "ami-id: $(get_ec2_metadata ami-id)"
|
|
||||||
echo "instance-id: $(get_ec2_metadata instance-id)"
|
|
||||||
echo "instance-type: $(get_ec2_metadata instance-type)"
|
|
||||||
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
|
|
||||||
uses: seemethere/add-github-ssh-key@v1
|
|
||||||
with:
|
|
||||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
||||||
- name: Checkout PyTorch
|
|
||||||
uses: zhouzhuojie/checkout@05b13c9a0d21f08f6d5e64a1d5042246d13619d9
|
|
||||||
with:
|
|
||||||
ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
|
|
||||||
# deep clone, to allow use of git merge-base
|
|
||||||
fetch-depth: 0
|
|
||||||
submodules: recursive
|
|
||||||
- name: Clean PyTorch checkout
|
|
||||||
run: |
|
|
||||||
# Remove any artifacts from the previous checkouts
|
|
||||||
git clean -fxd
|
|
||||||
- name: Install Visual Studio 2019 toolchain
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
.\.circleci\scripts\vs_install.ps1
|
|
||||||
- name: Install Cuda
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
.circleci/scripts/windows_cuda_install.sh
|
|
||||||
- name: Install Cudnn
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
.circleci/scripts/windows_cudnn_install.sh
|
|
||||||
- uses: seemethere/download-artifact-s3@0504774707cbc8603d7dca922e8026eb8bf3b47b
|
|
||||||
name: Download PyTorch Build Artifacts
|
|
||||||
with:
|
|
||||||
name: ${{ env.BUILD_ENVIRONMENT }}
|
|
||||||
path: C:\${{ github.run_id }}\build-results
|
|
||||||
- name: Check build-results folder
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
tree /F C:\$Env:GITHUB_RUN_ID\build-results
|
|
||||||
# Needed for coverage in win-test.sh
|
|
||||||
- uses: actions/setup-python@v2
|
|
||||||
name: Setup Python3
|
|
||||||
with:
|
|
||||||
python-version: '3.x'
|
|
||||||
- name: Test
|
|
||||||
shell: bash
|
|
||||||
env:
|
|
||||||
PYTORCH_FINAL_PACKAGE_DIR: /c/${{ github.run_id }}/build-results/
|
|
||||||
# Time out the test phase after 3.5 hours
|
|
||||||
timeout-minutes: 210
|
|
||||||
run: |
|
|
||||||
.jenkins/pytorch/win-test.sh
|
|
||||||
- name: Zip JSONs for upload
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
FILE_SUFFIX: '${{ github.job }}-distributed-1-1-windows.8xlarge.nvidia.gpu'
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
# -ir => recursive include all files in pattern
|
|
||||||
7z a "test-jsons-$Env:FILE_SUFFIX.zip" -ir'!test\*.json'
|
|
||||||
- uses: seemethere/upload-artifact-s3@v3
|
|
||||||
name: Store Test Downloaded JSONs on S3
|
|
||||||
if: always()
|
|
||||||
with:
|
|
||||||
retention-days: 14
|
|
||||||
if-no-files-found: warn
|
|
||||||
path:
|
|
||||||
test-jsons-*.zip
|
|
||||||
- name: Zip test reports for upload
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
FILE_SUFFIX: '${{ github.job }}-distributed-1-1-windows.8xlarge.nvidia.gpu'
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
# -ir => recursive include all files in pattern
|
|
||||||
7z a "test-reports-$Env:FILE_SUFFIX.zip" -ir'!test\*.xml'
|
|
||||||
- uses: seemethere/upload-artifact-s3@v3
|
|
||||||
name: Store Test Reports on S3
|
|
||||||
if: always()
|
|
||||||
with:
|
|
||||||
retention-days: 14
|
|
||||||
if-no-files-found: error
|
|
||||||
path:
|
|
||||||
test-reports-*.zip
|
|
||||||
- name: Install render_test_results dependencies
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
python3 -m pip install junitparser==2.1.1 rich==10.9.0
|
|
||||||
- name: "[[ Click me for rendered test results (useful for finding failing tests) ]]"
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
# Encoding is weird on windows, just try to default to utf-8 if possible
|
|
||||||
env:
|
|
||||||
PYTHONIOENCODING: "utf-8"
|
|
||||||
run: |
|
|
||||||
python3 tools/render_junit.py test/
|
|
||||||
- name: Wait until all sessions have drained
|
|
||||||
shell: powershell
|
|
||||||
if: always()
|
|
||||||
timeout-minutes: 120
|
|
||||||
run: |
|
|
||||||
.github\scripts\wait_for_ssh_to_drain.ps1
|
|
||||||
- name: Kill active ssh sessions if still around (Useful if workflow was cancelled)
|
|
||||||
shell: powershell
|
|
||||||
if: always()
|
|
||||||
run: |
|
|
||||||
.github\scripts\kill_active_ssh_sessions.ps1
|
|
||||||
- name: Parse ref
|
|
||||||
id: parse-ref
|
|
||||||
run: .github/scripts/parse_ref.py
|
|
||||||
- name: Upload test statistics
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
AWS_DEFAULT_REGION: us-east-1
|
|
||||||
BRANCH: ${{ steps.parse-ref.outputs.branch }}
|
|
||||||
JOB_BASE_NAME: periodic-win-vs2019-cuda11.1-py3-test
|
|
||||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
|
||||||
SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
|
|
||||||
TAG: ${{ steps.parse-ref.outputs.tag }}
|
|
||||||
WORKFLOW_ID: '${{ github.run_id }}'
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
python3 -m pip install -r requirements.txt
|
|
||||||
python3 -m pip install boto3==1.19.12
|
|
||||||
python3 -m tools.stats.print_test_stats --upload-to-s3 --compare-with-s3 test
|
|
||||||
- name: Cleanup workspace
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
# Should remove the entirety of pytorch-${{ github.run_id }}
|
|
||||||
run: |
|
|
||||||
rm -rf ./*
|
|
||||||
test_default_1_2:
|
test_default_1_2:
|
||||||
name: test (default, 1, 2, windows.8xlarge.nvidia.gpu)
|
name: test (default, 1, 2, windows.8xlarge.nvidia.gpu)
|
||||||
timeout-minutes: 240
|
timeout-minutes: 240
|
||||||
|
|
|
||||||
156
.github/workflows/generated-periodic-win-vs2019-cuda11.5-py3.yml
generated
vendored
156
.github/workflows/generated-periodic-win-vs2019-cuda11.5-py3.yml
generated
vendored
|
|
@ -279,162 +279,6 @@ jobs:
|
||||||
# Should remove the entirety of pytorch-${{ github.run_id }}
|
# Should remove the entirety of pytorch-${{ github.run_id }}
|
||||||
run: |
|
run: |
|
||||||
rm -rf ./*
|
rm -rf ./*
|
||||||
test_distributed_1_1:
|
|
||||||
name: test (distributed, 1, 1, windows.8xlarge.nvidia.gpu)
|
|
||||||
timeout-minutes: 240
|
|
||||||
env:
|
|
||||||
JOB_BASE_NAME: periodic-win-vs2019-cuda11.5-py3-test
|
|
||||||
SHARD_NUMBER: 1
|
|
||||||
NUM_TEST_SHARDS: 1
|
|
||||||
TEST_CONFIG: distributed
|
|
||||||
http_proxy: "http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128"
|
|
||||||
https_proxy: "http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128"
|
|
||||||
PR_BODY: ${{ github.event.pull_request.body }}
|
|
||||||
needs: build
|
|
||||||
runs-on: windows.8xlarge.nvidia.gpu
|
|
||||||
steps:
|
|
||||||
- name: Display EC2 information
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
set -euo pipefail
|
|
||||||
function get_ec2_metadata() {
|
|
||||||
# Pulled from instance metadata endpoint for EC2
|
|
||||||
# see https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/instancedata-data-retrieval.html
|
|
||||||
category=$1
|
|
||||||
curl -fsSL "http://169.254.169.254/latest/meta-data/${category}"
|
|
||||||
}
|
|
||||||
echo "ami-id: $(get_ec2_metadata ami-id)"
|
|
||||||
echo "instance-id: $(get_ec2_metadata instance-id)"
|
|
||||||
echo "instance-type: $(get_ec2_metadata instance-type)"
|
|
||||||
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
|
|
||||||
uses: seemethere/add-github-ssh-key@v1
|
|
||||||
with:
|
|
||||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
||||||
- name: Checkout PyTorch
|
|
||||||
uses: zhouzhuojie/checkout@05b13c9a0d21f08f6d5e64a1d5042246d13619d9
|
|
||||||
with:
|
|
||||||
ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
|
|
||||||
# deep clone, to allow use of git merge-base
|
|
||||||
fetch-depth: 0
|
|
||||||
submodules: recursive
|
|
||||||
- name: Clean PyTorch checkout
|
|
||||||
run: |
|
|
||||||
# Remove any artifacts from the previous checkouts
|
|
||||||
git clean -fxd
|
|
||||||
- name: Install Visual Studio 2019 toolchain
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
.\.circleci\scripts\vs_install.ps1
|
|
||||||
- name: Install Cuda
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
.circleci/scripts/windows_cuda_install.sh
|
|
||||||
- name: Install Cudnn
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
.circleci/scripts/windows_cudnn_install.sh
|
|
||||||
- uses: seemethere/download-artifact-s3@0504774707cbc8603d7dca922e8026eb8bf3b47b
|
|
||||||
name: Download PyTorch Build Artifacts
|
|
||||||
with:
|
|
||||||
name: ${{ env.BUILD_ENVIRONMENT }}
|
|
||||||
path: C:\${{ github.run_id }}\build-results
|
|
||||||
- name: Check build-results folder
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
tree /F C:\$Env:GITHUB_RUN_ID\build-results
|
|
||||||
# Needed for coverage in win-test.sh
|
|
||||||
- uses: actions/setup-python@v2
|
|
||||||
name: Setup Python3
|
|
||||||
with:
|
|
||||||
python-version: '3.x'
|
|
||||||
- name: Test
|
|
||||||
shell: bash
|
|
||||||
env:
|
|
||||||
PYTORCH_FINAL_PACKAGE_DIR: /c/${{ github.run_id }}/build-results/
|
|
||||||
# Time out the test phase after 3.5 hours
|
|
||||||
timeout-minutes: 210
|
|
||||||
run: |
|
|
||||||
.jenkins/pytorch/win-test.sh
|
|
||||||
- name: Zip JSONs for upload
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
FILE_SUFFIX: '${{ github.job }}-distributed-1-1-windows.8xlarge.nvidia.gpu'
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
# -ir => recursive include all files in pattern
|
|
||||||
7z a "test-jsons-$Env:FILE_SUFFIX.zip" -ir'!test\*.json'
|
|
||||||
- uses: seemethere/upload-artifact-s3@v3
|
|
||||||
name: Store Test Downloaded JSONs on S3
|
|
||||||
if: always()
|
|
||||||
with:
|
|
||||||
retention-days: 14
|
|
||||||
if-no-files-found: warn
|
|
||||||
path:
|
|
||||||
test-jsons-*.zip
|
|
||||||
- name: Zip test reports for upload
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
FILE_SUFFIX: '${{ github.job }}-distributed-1-1-windows.8xlarge.nvidia.gpu'
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
# -ir => recursive include all files in pattern
|
|
||||||
7z a "test-reports-$Env:FILE_SUFFIX.zip" -ir'!test\*.xml'
|
|
||||||
- uses: seemethere/upload-artifact-s3@v3
|
|
||||||
name: Store Test Reports on S3
|
|
||||||
if: always()
|
|
||||||
with:
|
|
||||||
retention-days: 14
|
|
||||||
if-no-files-found: error
|
|
||||||
path:
|
|
||||||
test-reports-*.zip
|
|
||||||
- name: Install render_test_results dependencies
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
python3 -m pip install junitparser==2.1.1 rich==10.9.0
|
|
||||||
- name: "[[ Click me for rendered test results (useful for finding failing tests) ]]"
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
# Encoding is weird on windows, just try to default to utf-8 if possible
|
|
||||||
env:
|
|
||||||
PYTHONIOENCODING: "utf-8"
|
|
||||||
run: |
|
|
||||||
python3 tools/render_junit.py test/
|
|
||||||
- name: Wait until all sessions have drained
|
|
||||||
shell: powershell
|
|
||||||
if: always()
|
|
||||||
timeout-minutes: 120
|
|
||||||
run: |
|
|
||||||
.github\scripts\wait_for_ssh_to_drain.ps1
|
|
||||||
- name: Kill active ssh sessions if still around (Useful if workflow was cancelled)
|
|
||||||
shell: powershell
|
|
||||||
if: always()
|
|
||||||
run: |
|
|
||||||
.github\scripts\kill_active_ssh_sessions.ps1
|
|
||||||
- name: Parse ref
|
|
||||||
id: parse-ref
|
|
||||||
run: .github/scripts/parse_ref.py
|
|
||||||
- name: Upload test statistics
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
AWS_DEFAULT_REGION: us-east-1
|
|
||||||
BRANCH: ${{ steps.parse-ref.outputs.branch }}
|
|
||||||
JOB_BASE_NAME: periodic-win-vs2019-cuda11.5-py3-test
|
|
||||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
|
||||||
SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
|
|
||||||
TAG: ${{ steps.parse-ref.outputs.tag }}
|
|
||||||
WORKFLOW_ID: '${{ github.run_id }}'
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
python3 -m pip install -r requirements.txt
|
|
||||||
python3 -m pip install boto3==1.19.12
|
|
||||||
python3 -m tools.stats.print_test_stats --upload-to-s3 --compare-with-s3 test
|
|
||||||
- name: Cleanup workspace
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
# Should remove the entirety of pytorch-${{ github.run_id }}
|
|
||||||
run: |
|
|
||||||
rm -rf ./*
|
|
||||||
test_default_1_2:
|
test_default_1_2:
|
||||||
name: test (default, 1, 2, windows.8xlarge.nvidia.gpu)
|
name: test (default, 1, 2, windows.8xlarge.nvidia.gpu)
|
||||||
timeout-minutes: 240
|
timeout-minutes: 240
|
||||||
|
|
|
||||||
148
.github/workflows/generated-win-vs2019-cpu-py3.yml
generated
vendored
148
.github/workflows/generated-win-vs2019-cpu-py3.yml
generated
vendored
|
|
@ -124,154 +124,6 @@ jobs:
|
||||||
run: |
|
run: |
|
||||||
rm -rf "${PYTORCH_FINAL_PACKAGE_DIR}"
|
rm -rf "${PYTORCH_FINAL_PACKAGE_DIR}"
|
||||||
rm -rf ./*
|
rm -rf ./*
|
||||||
test_distributed_1_1:
|
|
||||||
name: test (distributed, 1, 1, windows.4xlarge)
|
|
||||||
timeout-minutes: 240
|
|
||||||
env:
|
|
||||||
JOB_BASE_NAME: win-vs2019-cpu-py3-test
|
|
||||||
SHARD_NUMBER: 1
|
|
||||||
NUM_TEST_SHARDS: 1
|
|
||||||
TEST_CONFIG: distributed
|
|
||||||
http_proxy: "http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128"
|
|
||||||
https_proxy: "http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128"
|
|
||||||
PR_BODY: ${{ github.event.pull_request.body }}
|
|
||||||
needs: build
|
|
||||||
runs-on: windows.4xlarge
|
|
||||||
steps:
|
|
||||||
- name: Display EC2 information
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
set -euo pipefail
|
|
||||||
function get_ec2_metadata() {
|
|
||||||
# Pulled from instance metadata endpoint for EC2
|
|
||||||
# see https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/instancedata-data-retrieval.html
|
|
||||||
category=$1
|
|
||||||
curl -fsSL "http://169.254.169.254/latest/meta-data/${category}"
|
|
||||||
}
|
|
||||||
echo "ami-id: $(get_ec2_metadata ami-id)"
|
|
||||||
echo "instance-id: $(get_ec2_metadata instance-id)"
|
|
||||||
echo "instance-type: $(get_ec2_metadata instance-type)"
|
|
||||||
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
|
|
||||||
uses: seemethere/add-github-ssh-key@v1
|
|
||||||
with:
|
|
||||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
||||||
- name: Checkout PyTorch
|
|
||||||
uses: zhouzhuojie/checkout@05b13c9a0d21f08f6d5e64a1d5042246d13619d9
|
|
||||||
with:
|
|
||||||
ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
|
|
||||||
# deep clone, to allow use of git merge-base
|
|
||||||
fetch-depth: 0
|
|
||||||
submodules: recursive
|
|
||||||
- name: Clean PyTorch checkout
|
|
||||||
run: |
|
|
||||||
# Remove any artifacts from the previous checkouts
|
|
||||||
git clean -fxd
|
|
||||||
- name: Install Visual Studio 2019 toolchain
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
.\.circleci\scripts\vs_install.ps1
|
|
||||||
- uses: seemethere/download-artifact-s3@0504774707cbc8603d7dca922e8026eb8bf3b47b
|
|
||||||
name: Download PyTorch Build Artifacts
|
|
||||||
with:
|
|
||||||
name: ${{ env.BUILD_ENVIRONMENT }}
|
|
||||||
path: C:\${{ github.run_id }}\build-results
|
|
||||||
- name: Check build-results folder
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
tree /F C:\$Env:GITHUB_RUN_ID\build-results
|
|
||||||
# Needed for coverage in win-test.sh
|
|
||||||
- uses: actions/setup-python@v2
|
|
||||||
name: Setup Python3
|
|
||||||
with:
|
|
||||||
python-version: '3.x'
|
|
||||||
- name: Test
|
|
||||||
shell: bash
|
|
||||||
env:
|
|
||||||
PYTORCH_FINAL_PACKAGE_DIR: /c/${{ github.run_id }}/build-results/
|
|
||||||
# Time out the test phase after 3.5 hours
|
|
||||||
timeout-minutes: 210
|
|
||||||
run: |
|
|
||||||
.jenkins/pytorch/win-test.sh
|
|
||||||
- name: Zip JSONs for upload
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
FILE_SUFFIX: '${{ github.job }}-distributed-1-1-windows.4xlarge'
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
# -ir => recursive include all files in pattern
|
|
||||||
7z a "test-jsons-$Env:FILE_SUFFIX.zip" -ir'!test\*.json'
|
|
||||||
- uses: seemethere/upload-artifact-s3@v3
|
|
||||||
name: Store Test Downloaded JSONs on S3
|
|
||||||
if: always()
|
|
||||||
with:
|
|
||||||
retention-days: 14
|
|
||||||
if-no-files-found: warn
|
|
||||||
path:
|
|
||||||
test-jsons-*.zip
|
|
||||||
- name: Zip test reports for upload
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
FILE_SUFFIX: '${{ github.job }}-distributed-1-1-windows.4xlarge'
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
# -ir => recursive include all files in pattern
|
|
||||||
7z a "test-reports-$Env:FILE_SUFFIX.zip" -ir'!test\*.xml'
|
|
||||||
- uses: seemethere/upload-artifact-s3@v3
|
|
||||||
name: Store Test Reports on S3
|
|
||||||
if: always()
|
|
||||||
with:
|
|
||||||
retention-days: 14
|
|
||||||
if-no-files-found: error
|
|
||||||
path:
|
|
||||||
test-reports-*.zip
|
|
||||||
- name: Install render_test_results dependencies
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
python3 -m pip install junitparser==2.1.1 rich==10.9.0
|
|
||||||
- name: "[[ Click me for rendered test results (useful for finding failing tests) ]]"
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
# Encoding is weird on windows, just try to default to utf-8 if possible
|
|
||||||
env:
|
|
||||||
PYTHONIOENCODING: "utf-8"
|
|
||||||
run: |
|
|
||||||
python3 tools/render_junit.py test/
|
|
||||||
- name: Wait until all sessions have drained
|
|
||||||
shell: powershell
|
|
||||||
if: always()
|
|
||||||
timeout-minutes: 120
|
|
||||||
run: |
|
|
||||||
.github\scripts\wait_for_ssh_to_drain.ps1
|
|
||||||
- name: Kill active ssh sessions if still around (Useful if workflow was cancelled)
|
|
||||||
shell: powershell
|
|
||||||
if: always()
|
|
||||||
run: |
|
|
||||||
.github\scripts\kill_active_ssh_sessions.ps1
|
|
||||||
- name: Parse ref
|
|
||||||
id: parse-ref
|
|
||||||
run: .github/scripts/parse_ref.py
|
|
||||||
- name: Upload test statistics
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
AWS_DEFAULT_REGION: us-east-1
|
|
||||||
BRANCH: ${{ steps.parse-ref.outputs.branch }}
|
|
||||||
JOB_BASE_NAME: win-vs2019-cpu-py3-test
|
|
||||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
|
||||||
SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
|
|
||||||
TAG: ${{ steps.parse-ref.outputs.tag }}
|
|
||||||
WORKFLOW_ID: '${{ github.run_id }}'
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
python3 -m pip install -r requirements.txt
|
|
||||||
python3 -m pip install boto3==1.19.12
|
|
||||||
python3 -m tools.stats.print_test_stats --upload-to-s3 --compare-with-s3 test
|
|
||||||
- name: Cleanup workspace
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
# Should remove the entirety of pytorch-${{ github.run_id }}
|
|
||||||
run: |
|
|
||||||
rm -rf ./*
|
|
||||||
test_default_1_2:
|
test_default_1_2:
|
||||||
name: test (default, 1, 2, windows.4xlarge)
|
name: test (default, 1, 2, windows.4xlarge)
|
||||||
timeout-minutes: 240
|
timeout-minutes: 240
|
||||||
|
|
|
||||||
156
.github/workflows/generated-win-vs2019-cuda11.3-py3.yml
generated
vendored
156
.github/workflows/generated-win-vs2019-cuda11.3-py3.yml
generated
vendored
|
|
@ -281,162 +281,6 @@ jobs:
|
||||||
# Should remove the entirety of pytorch-${{ github.run_id }}
|
# Should remove the entirety of pytorch-${{ github.run_id }}
|
||||||
run: |
|
run: |
|
||||||
rm -rf ./*
|
rm -rf ./*
|
||||||
test_distributed_1_1:
|
|
||||||
name: test (distributed, 1, 1, windows.8xlarge.nvidia.gpu)
|
|
||||||
timeout-minutes: 240
|
|
||||||
env:
|
|
||||||
JOB_BASE_NAME: win-vs2019-cuda11.3-py3-test
|
|
||||||
SHARD_NUMBER: 1
|
|
||||||
NUM_TEST_SHARDS: 1
|
|
||||||
TEST_CONFIG: distributed
|
|
||||||
http_proxy: "http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128"
|
|
||||||
https_proxy: "http://internal-tf-lb-20210727220640487900000002-835786077.us-east-1.elb.amazonaws.com:3128"
|
|
||||||
PR_BODY: ${{ github.event.pull_request.body }}
|
|
||||||
needs: build
|
|
||||||
runs-on: windows.8xlarge.nvidia.gpu
|
|
||||||
steps:
|
|
||||||
- name: Display EC2 information
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
set -euo pipefail
|
|
||||||
function get_ec2_metadata() {
|
|
||||||
# Pulled from instance metadata endpoint for EC2
|
|
||||||
# see https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/instancedata-data-retrieval.html
|
|
||||||
category=$1
|
|
||||||
curl -fsSL "http://169.254.169.254/latest/meta-data/${category}"
|
|
||||||
}
|
|
||||||
echo "ami-id: $(get_ec2_metadata ami-id)"
|
|
||||||
echo "instance-id: $(get_ec2_metadata instance-id)"
|
|
||||||
echo "instance-type: $(get_ec2_metadata instance-type)"
|
|
||||||
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
|
|
||||||
uses: seemethere/add-github-ssh-key@v1
|
|
||||||
with:
|
|
||||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
||||||
- name: Checkout PyTorch
|
|
||||||
uses: zhouzhuojie/checkout@05b13c9a0d21f08f6d5e64a1d5042246d13619d9
|
|
||||||
with:
|
|
||||||
ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
|
|
||||||
# deep clone, to allow use of git merge-base
|
|
||||||
fetch-depth: 0
|
|
||||||
submodules: recursive
|
|
||||||
- name: Clean PyTorch checkout
|
|
||||||
run: |
|
|
||||||
# Remove any artifacts from the previous checkouts
|
|
||||||
git clean -fxd
|
|
||||||
- name: Install Visual Studio 2019 toolchain
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
.\.circleci\scripts\vs_install.ps1
|
|
||||||
- name: Install Cuda
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
.circleci/scripts/windows_cuda_install.sh
|
|
||||||
- name: Install Cudnn
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
.circleci/scripts/windows_cudnn_install.sh
|
|
||||||
- uses: seemethere/download-artifact-s3@0504774707cbc8603d7dca922e8026eb8bf3b47b
|
|
||||||
name: Download PyTorch Build Artifacts
|
|
||||||
with:
|
|
||||||
name: ${{ env.BUILD_ENVIRONMENT }}
|
|
||||||
path: C:\${{ github.run_id }}\build-results
|
|
||||||
- name: Check build-results folder
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
tree /F C:\$Env:GITHUB_RUN_ID\build-results
|
|
||||||
# Needed for coverage in win-test.sh
|
|
||||||
- uses: actions/setup-python@v2
|
|
||||||
name: Setup Python3
|
|
||||||
with:
|
|
||||||
python-version: '3.x'
|
|
||||||
- name: Test
|
|
||||||
shell: bash
|
|
||||||
env:
|
|
||||||
PYTORCH_FINAL_PACKAGE_DIR: /c/${{ github.run_id }}/build-results/
|
|
||||||
# Time out the test phase after 3.5 hours
|
|
||||||
timeout-minutes: 210
|
|
||||||
run: |
|
|
||||||
.jenkins/pytorch/win-test.sh
|
|
||||||
- name: Zip JSONs for upload
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
FILE_SUFFIX: '${{ github.job }}-distributed-1-1-windows.8xlarge.nvidia.gpu'
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
# -ir => recursive include all files in pattern
|
|
||||||
7z a "test-jsons-$Env:FILE_SUFFIX.zip" -ir'!test\*.json'
|
|
||||||
- uses: seemethere/upload-artifact-s3@v3
|
|
||||||
name: Store Test Downloaded JSONs on S3
|
|
||||||
if: always()
|
|
||||||
with:
|
|
||||||
retention-days: 14
|
|
||||||
if-no-files-found: warn
|
|
||||||
path:
|
|
||||||
test-jsons-*.zip
|
|
||||||
- name: Zip test reports for upload
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
FILE_SUFFIX: '${{ github.job }}-distributed-1-1-windows.8xlarge.nvidia.gpu'
|
|
||||||
shell: powershell
|
|
||||||
run: |
|
|
||||||
# -ir => recursive include all files in pattern
|
|
||||||
7z a "test-reports-$Env:FILE_SUFFIX.zip" -ir'!test\*.xml'
|
|
||||||
- uses: seemethere/upload-artifact-s3@v3
|
|
||||||
name: Store Test Reports on S3
|
|
||||||
if: always()
|
|
||||||
with:
|
|
||||||
retention-days: 14
|
|
||||||
if-no-files-found: error
|
|
||||||
path:
|
|
||||||
test-reports-*.zip
|
|
||||||
- name: Install render_test_results dependencies
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
python3 -m pip install junitparser==2.1.1 rich==10.9.0
|
|
||||||
- name: "[[ Click me for rendered test results (useful for finding failing tests) ]]"
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
# Encoding is weird on windows, just try to default to utf-8 if possible
|
|
||||||
env:
|
|
||||||
PYTHONIOENCODING: "utf-8"
|
|
||||||
run: |
|
|
||||||
python3 tools/render_junit.py test/
|
|
||||||
- name: Wait until all sessions have drained
|
|
||||||
shell: powershell
|
|
||||||
if: always()
|
|
||||||
timeout-minutes: 120
|
|
||||||
run: |
|
|
||||||
.github\scripts\wait_for_ssh_to_drain.ps1
|
|
||||||
- name: Kill active ssh sessions if still around (Useful if workflow was cancelled)
|
|
||||||
shell: powershell
|
|
||||||
if: always()
|
|
||||||
run: |
|
|
||||||
.github\scripts\kill_active_ssh_sessions.ps1
|
|
||||||
- name: Parse ref
|
|
||||||
id: parse-ref
|
|
||||||
run: .github/scripts/parse_ref.py
|
|
||||||
- name: Upload test statistics
|
|
||||||
if: always()
|
|
||||||
env:
|
|
||||||
AWS_DEFAULT_REGION: us-east-1
|
|
||||||
BRANCH: ${{ steps.parse-ref.outputs.branch }}
|
|
||||||
JOB_BASE_NAME: win-vs2019-cuda11.3-py3-test
|
|
||||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
|
||||||
SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
|
|
||||||
TAG: ${{ steps.parse-ref.outputs.tag }}
|
|
||||||
WORKFLOW_ID: '${{ github.run_id }}'
|
|
||||||
shell: bash
|
|
||||||
run: |
|
|
||||||
python3 -m pip install -r requirements.txt
|
|
||||||
python3 -m pip install boto3==1.19.12
|
|
||||||
python3 -m tools.stats.print_test_stats --upload-to-s3 --compare-with-s3 test
|
|
||||||
- name: Cleanup workspace
|
|
||||||
if: always()
|
|
||||||
shell: bash
|
|
||||||
# Should remove the entirety of pytorch-${{ github.run_id }}
|
|
||||||
run: |
|
|
||||||
rm -rf ./*
|
|
||||||
test_default_1_2:
|
test_default_1_2:
|
||||||
name: test (default, 1, 2, windows.8xlarge.nvidia.gpu)
|
name: test (default, 1, 2, windows.8xlarge.nvidia.gpu)
|
||||||
timeout-minutes: 240
|
timeout-minutes: 240
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user