mirror of
https://github.com/NVIDIA/OpenShell.git
synced 2026-10-16 05:20:22 +08:00
Evan Lezar
a226806026
* test(e2e): add workload manifest build flow Signed-off-by: Evan Lezar <elezar@nvidia.com> * test(e2e): add gpu workload validation tests Signed-off-by: Evan Lezar <elezar@nvidia.com> * ci(e2e): build gpu workloads before gpu e2e Signed-off-by: Evan Lezar <elezar@nvidia.com> --------- Signed-off-by: Evan Lezar <elezar@nvidia.com>
74 lines
2.5 KiB
YAML
74 lines
2.5 KiB
YAML
name: GPU E2E Test
|
|
|
|
on:
|
|
workflow_call:
|
|
inputs:
|
|
image-tag:
|
|
description: "Image tag to test (typically the commit SHA)"
|
|
required: true
|
|
type: string
|
|
|
|
permissions:
|
|
contents: read
|
|
packages: read
|
|
|
|
jobs:
|
|
e2e-gpu:
|
|
name: "E2E Docker GPU (${{ matrix.name }})"
|
|
runs-on: ${{ matrix.runner }}
|
|
continue-on-error: ${{ matrix.experimental }}
|
|
timeout-minutes: 30
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
include:
|
|
- name: linux-arm64
|
|
runner: linux-arm64-gpu-l4-latest-1
|
|
experimental: false
|
|
- name: linux-amd64
|
|
runner: linux-amd64-gpu-rtxpro6000-latest-1
|
|
experimental: false
|
|
- name: wsl-amd64
|
|
runner: wsl-amd64-gpu-rtxpro6000-latest-1
|
|
experimental: true
|
|
container:
|
|
image: ghcr.io/nvidia/openshell/ci:latest
|
|
credentials:
|
|
username: ${{ github.actor }}
|
|
password: ${{ secrets.GITHUB_TOKEN }}
|
|
options: --privileged
|
|
volumes:
|
|
- /var/run/docker.sock:/var/run/docker.sock
|
|
- /home/runner/_work:/home/runner/_work
|
|
env:
|
|
MISE_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
IMAGE_TAG: ${{ inputs.image-tag }}
|
|
OPENSHELL_REGISTRY: ghcr.io/nvidia/openshell
|
|
OPENSHELL_REGISTRY_HOST: ghcr.io
|
|
OPENSHELL_REGISTRY_NAMESPACE: nvidia/openshell
|
|
OPENSHELL_REGISTRY_USERNAME: ${{ github.actor }}
|
|
OPENSHELL_REGISTRY_PASSWORD: ${{ secrets.GITHUB_TOKEN }}
|
|
CONTAINER_ENGINE: docker
|
|
OPENSHELL_E2E_DOCKER_GPU: "1"
|
|
# NVIDIA-managed Ubuntu base used as the GPU probe target: it has the
|
|
# filesystem layout CDI injection expects (ldconfig, populated /usr/bin)
|
|
# which the distroless gateway runtime lacks. Consumed by the prereq
|
|
# probe below and by the e2e tests in e2e/rust/tests/gpu/device_selection.rs.
|
|
OPENSHELL_E2E_GPU_PROBE_IMAGE: "nvcr.io/nvidia/base/ubuntu:noble-20251013"
|
|
steps:
|
|
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
|
|
|
- name: Log in to GHCR
|
|
run: echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u "${{ github.actor }}" --password-stdin
|
|
|
|
- name: Check Docker GPU prerequisites
|
|
run: |
|
|
docker info --format '{{json .CDISpecDirs}}'
|
|
docker run --rm --device nvidia.com/gpu=all "${OPENSHELL_E2E_GPU_PROBE_IMAGE}" nvidia-smi -L
|
|
|
|
- name: Build GPU workload images
|
|
run: mise run --no-deps --skip-deps e2e:workloads:build
|
|
|
|
- name: Run tests
|
|
run: mise run --no-deps --skip-deps e2e:docker:gpu
|