Skip to content

[aoti] Add error msg if we can't find a proxy executor (#140308) #1

[aoti] Add error msg if we can't find a proxy executor (#140308)

[aoti] Add error msg if we can't find a proxy executor (#140308) #1

# @generated DO NOT EDIT MANUALLY
# Template is at: .github/templates/windows_binary_build_workflow.yml.j2
# Generation script: .github/scripts/generate_ci_workflows.py
name: windows-binary-libtorch-debug
on:
push:
branches:
- main
workflow_dispatch:
env:
# Needed for conda builds
ALPINE_IMAGE: "308535385114.dkr.ecr.us-east-1.amazonaws.com/tool/alpine"
ANACONDA_USER: pytorch
AWS_DEFAULT_REGION: us-east-1
BUILD_ENVIRONMENT: windows-binary-libtorch-debug
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
PR_NUMBER: ${{ github.event.pull_request.number }}
SHA1: ${{ github.event.pull_request.head.sha || github.sha }}
SKIP_ALL_TESTS: 1
concurrency:
group: windows-binary-libtorch-debug-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }}
cancel-in-progress: true
jobs:
get-label-type:
if: github.repository_owner == 'pytorch'
name: get-label-type
uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main
with:
triggering_actor: ${{ github.triggering_actor }}
issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
curr_branch: ${{ github.head_ref || github.ref_name }}
curr_ref_type: ${{ github.ref_type }}
libtorch-cpu-shared-with-deps-debug-build:
if: ${{ github.repository_owner == 'pytorch' }}
needs: get-label-type
runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
timeout-minutes: 240
env:
PYTORCH_ROOT: ${{ github.workspace }}/pytorch
BUILDER_ROOT: ${{ github.workspace }}/builder
PACKAGE_TYPE: libtorch
# TODO: This is a legacy variable that we eventually want to get rid of in
# favor of GPU_ARCH_VERSION
DESIRED_CUDA: cpu
GPU_ARCH_TYPE: cpu
SKIP_ALL_TESTS: 1
LIBTORCH_CONFIG: debug
LIBTORCH_VARIANT: shared-with-deps
# This is a dummy value for libtorch to work correctly with our batch scripts
# without this value pip does not get installed for some reason
DESIRED_PYTHON: "3.9"
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 -H "X-aws-ec2-metadata-token: $(curl -s -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 30")" -fsSL "http://169.254.169.254/latest/meta-data/${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)"
echo "system info $(uname -a)"
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
uses: pytorch/test-infra/.github/actions/setup-ssh@main
continue-on-error: true
with:
github-secret: ${{ secrets.GITHUB_TOKEN }}
- name: Enable git long paths and symlinks on Windows and disable fsmonitor daemon
shell: bash
run: |
git config --global core.longpaths true
git config --global core.symlinks true
# https://git-scm.com/docs/git-fsmonitor--daemon. The daemon could lock
# the directory on Windows and prevent GHA from checking out as reported
# in https://github.com/actions/checkout/issues/1018
git config --global core.fsmonitor false
# Needed for binary builds, see: https://github.com/pytorch/pytorch/issues/73339#issuecomment-1058981560
- name: Enable long paths on Windows
shell: powershell
run: |
Set-ItemProperty -Path "HKLM:\\SYSTEM\CurrentControlSet\Control\FileSystem" -Name "LongPathsEnabled" -Value 1
# Since it's just a defensive command, the workflow should continue even the command fails. This step can be
# removed once Windows Defender is removed from the AMI
- name: Disables Windows Defender scheduled and real-time scanning for files in directories used by PyTorch
continue-on-error: true
shell: powershell
run: |
Add-MpPreference -ExclusionPath $(Get-Location).tostring(),$Env:TEMP -ErrorAction Ignore
# Let's both exclude the path and disable Windows Defender completely just to be sure
# that it doesn't interfere
Set-MpPreference -DisableRealtimeMonitoring $True -ErrorAction Ignore
# NOTE: These environment variables are put here so that they can be applied on every job equally
# They are also here because setting them at a workflow level doesn't give us access to the
# runner.temp variable, which we need.
- name: Populate binary env
shell: bash
run: |
echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
- name: Checkout PyTorch
uses: malfet/checkout@silent-checkout
with:
ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
submodules: recursive
path: pytorch
quiet-checkout: true
- name: Clean PyTorch checkout
run: |
# Remove any artifacts from the previous checkouts
git clean -fxd
working-directory: pytorch
- name: Checkout pytorch/builder
uses: malfet/checkout@silent-checkout
with:
ref: main
submodules: recursive
repository: pytorch/builder
path: builder
quiet-checkout: true
- name: Clean pytorch/builder checkout
run: |
# Remove any artifacts from the previous checkouts
git clean -fxd
working-directory: builder
- name: Populate binary env
shell: bash
run: |
"${PYTORCH_ROOT}/.circleci/scripts/binary_populate_env.sh"
- name: Build PyTorch binary
shell: bash
run: |
"${PYTORCH_ROOT}/.circleci/scripts/binary_windows_build.sh"
- uses: actions/[email protected]
if: always()
with:
name: libtorch-cpu-shared-with-deps-debug
retention-days: 14
if-no-files-found: error
path: "${{ env.PYTORCH_FINAL_PACKAGE_DIR }}"
- name: Wait until all sessions have drained
shell: powershell
working-directory: pytorch
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
working-directory: pytorch
if: always()
run: |
.github\scripts\kill_active_ssh_sessions.ps1
libtorch-cpu-shared-with-deps-debug-test: # Testing
if: ${{ github.repository_owner == 'pytorch' }}
needs:
- libtorch-cpu-shared-with-deps-debug-build
- get-label-type
runs-on: "${{ needs.get-label-type.outputs.label-type }}windows.4xlarge.nonephemeral"
timeout-minutes: 240
env:
PYTORCH_ROOT: ${{ github.workspace }}/pytorch
BUILDER_ROOT: ${{ github.workspace }}/builder
PACKAGE_TYPE: libtorch
# TODO: This is a legacy variable that we eventually want to get rid of in
# favor of GPU_ARCH_VERSION
DESIRED_CUDA: cpu
GPU_ARCH_TYPE: cpu
SKIP_ALL_TESTS: 1
LIBTORCH_CONFIG: debug
LIBTORCH_VARIANT: shared-with-deps
# This is a dummy value for libtorch to work correctly with our batch scripts
# without this value pip does not get installed for some reason
DESIRED_PYTHON: "3.9"
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 -H "X-aws-ec2-metadata-token: $(curl -s -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 30")" -fsSL "http://169.254.169.254/latest/meta-data/${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)"
echo "system info $(uname -a)"
- name: "[FB EMPLOYEES] Enable SSH (Click me for login details)"
uses: pytorch/test-infra/.github/actions/setup-ssh@main
continue-on-error: true
with:
github-secret: ${{ secrets.GITHUB_TOKEN }}
- name: Enable git long paths and symlinks on Windows and disable fsmonitor daemon
shell: bash
run: |
git config --global core.longpaths true
git config --global core.symlinks true
# https://git-scm.com/docs/git-fsmonitor--daemon. The daemon could lock
# the directory on Windows and prevent GHA from checking out as reported
# in https://github.com/actions/checkout/issues/1018
git config --global core.fsmonitor false
# Needed for binary builds, see: https://github.com/pytorch/pytorch/issues/73339#issuecomment-1058981560
- name: Enable long paths on Windows
shell: powershell
run: |
Set-ItemProperty -Path "HKLM:\\SYSTEM\CurrentControlSet\Control\FileSystem" -Name "LongPathsEnabled" -Value 1
# Since it's just a defensive command, the workflow should continue even the command fails. This step can be
# removed once Windows Defender is removed from the AMI
- name: Disables Windows Defender scheduled and real-time scanning for files in directories used by PyTorch
continue-on-error: true
shell: powershell
run: |
Add-MpPreference -ExclusionPath $(Get-Location).tostring(),$Env:TEMP -ErrorAction Ignore
# Let's both exclude the path and disable Windows Defender completely just to be sure
# that it doesn't interfere
Set-MpPreference -DisableRealtimeMonitoring $True -ErrorAction Ignore
# NOTE: These environment variables are put here so that they can be applied on every job equally
# They are also here because setting them at a workflow level doesn't give us access to the
# runner.temp variable, which we need.
- name: Populate binary env
shell: bash
run: |
echo "BINARY_ENV_FILE=${RUNNER_TEMP}/env" >> "${GITHUB_ENV}"
echo "PYTORCH_FINAL_PACKAGE_DIR=${RUNNER_TEMP}/artifacts" >> "${GITHUB_ENV}"
echo "WIN_PACKAGE_WORK_DIR=${RUNNER_TEMP}"
- uses: actions/[email protected]
name: Download Build Artifacts
with:
name: libtorch-cpu-shared-with-deps-debug
path: "${{ env.PYTORCH_FINAL_PACKAGE_DIR }}"
- name: Checkout PyTorch
uses: malfet/checkout@silent-checkout
with:
ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
submodules: recursive
path: pytorch
quiet-checkout: true
- name: Clean PyTorch checkout
run: |
# Remove any artifacts from the previous checkouts
git clean -fxd
working-directory: pytorch
- name: Checkout pytorch/builder
uses: malfet/checkout@silent-checkout
with:
ref: main
submodules: recursive
repository: pytorch/builder
path: builder
quiet-checkout: true
- name: Clean pytorch/builder checkout
run: |
# Remove any artifacts from the previous checkouts
git clean -fxd
working-directory: builder
- name: Populate binary env
shell: bash
run: |
"${PYTORCH_ROOT}/.circleci/scripts/binary_populate_env.sh"
- name: Test PyTorch binary
shell: bash
run: |
"${PYTORCH_ROOT}/.circleci/scripts/binary_windows_test.sh"
- name: Wait until all sessions have drained
shell: powershell
working-directory: pytorch
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
working-directory: pytorch
if: always()
run: |
.github\scripts\kill_active_ssh_sessions.ps1