Fallback to single shard CI test.

This commit is contained in:
Nicolas Patry 2024-10-03 12:53:20 +02:00
parent 7081b8fb4d
commit 06f9186d80
No known key found for this signature in database
GPG Key ID: E939E8CC91A1C674

View File

@ -18,161 +18,160 @@ on:
type: boolean
jobs:
# build-and-push:
# outputs:
# docker_image: ${{ steps.final.outputs.docker_image }}
# docker_devices: ${{ steps.final.outputs.docker_devices }}
# runs_on: ${{ steps.final.outputs.runs_on }}
# label: ${{ steps.final.outputs.label }}
# extra_pytest: ${{ steps.final.outputs.extra_pytest }}
# concurrency:
# group: ${{ github.workflow }}-build-and-push-image-${{ inputs.hardware }}-${{ github.head_ref || github.run_id }}
# cancel-in-progress: true
# runs-on:
# group: aws-highmemory-32-plus-priv
# permissions:
# contents: write
# packages: write
# steps:
# - name: Checkout repository
# uses: actions/checkout@v4
# - name: Inject slug/short variables
# uses: rlespinasse/github-slug-action@v4.4.1
# - name: Construct harware variables
# shell: bash
# run: |
# case ${{ inputs.hardware }} in
# cuda)
# export dockerfile="Dockerfile"
# export label_extension=""
# export docker_devices=""
# export runs_on="aws-g6-12xl-plus-priv-cache"
# export platform=""
# export extra_pytest=""
# ;;
# rocm)
# export dockerfile="Dockerfile_amd"
# export label_extension="-rocm"
# export docker_devices="/dev/kfd,/dev/dri"
# export runs_on="amd-gpu-runners"
# export platform=""
# export extra_pytest="-k flash_llama_grammar_tools"
# ;;
# intel-xpu)
# export dockerfile="Dockerfile_intel"
# export label_extension="-intel-xpu"
# export docker_devices=""
# export runs_on="ubuntu-latest"
# export platform="xpu"
# export extra_pytest=""
# ;;
# intel-cpu)
# export dockerfile="Dockerfile_intel"
# export label_extension="-intel-cpu"
# export docker_devices=""
# export runs_on="ubuntu-latest"
# export platform="cpu"
# export extra_pytest=""
# ;;
# esac
# echo $dockerfile
# echo "Dockerfile=${dockerfile}"
# echo $label_extension
# echo $docker_devices
# echo $runs_on
# echo $platform
# echo "DOCKERFILE=${dockerfile}" >> $GITHUB_ENV
# echo "LABEL=${label_extension}" >> $GITHUB_ENV
# echo "PLATFORM=${platform}" >> $GITHUB_ENV
# echo "DOCKER_DEVICES=${docker_devices}" >> $GITHUB_ENV
# echo "RUNS_ON=${runs_on}" >> $GITHUB_ENV
# echo "EXTRA_PYTEST=${extra_pytest}" >> $GITHUB_ENV
# echo REGISTRY_MIRROR=$REGISTRY_MIRROR >> $GITHUB_ENV
# - name: Initialize Docker Buildx
# uses: docker/setup-buildx-action@v3
# with:
# install: true
# buildkitd-config: /tmp/buildkitd.toml
# - name: Login to internal Container Registry
# uses: docker/login-action@v3
# with:
# username: ${{ secrets.REGISTRY_USERNAME }}
# password: ${{ secrets.REGISTRY_PASSWORD }}
# registry: registry.internal.huggingface.tech
# - name: Login to GitHub Container Registry
# if: github.event_name != 'pull_request'
# uses: docker/login-action@v3
# with:
# registry: ghcr.io
# username: ${{ github.actor }}
# password: ${{ secrets.GITHUB_TOKEN }}
# - name: Login to Azure Container Registry
# if: github.event_name != 'pull_request'
# uses: docker/login-action@v3
# with:
# username: ${{ secrets.AZURE_DOCKER_USERNAME }}
# password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
# registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
# # If pull request
# - name: Extract metadata (tags, labels) for Docker
# if: ${{ github.event_name == 'pull_request' }}
# id: meta-pr
# uses: docker/metadata-action@v5
# with:
# images: |
# registry.internal.huggingface.tech/api-inference/community/text-generation-inference
# tags: |
# type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
# # If main, release or tag
# - name: Extract metadata (tags, labels) for Docker
# if: ${{ github.event_name != 'pull_request' }}
# id: meta
# uses: docker/metadata-action@v4.3.0
# with:
# flavor: |
# latest=auto
# images: |
# registry.internal.huggingface.tech/api-inference/community/text-generation-inference
# ghcr.io/huggingface/text-generation-inference
# db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
# tags: |
# type=semver,pattern={{version}}${{ env.LABEL }}
# type=semver,pattern={{major}}.{{minor}}${{ env.LABEL }}
# type=raw,value=latest${{ env.LABEL }},enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
# type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
# - name: Build and push Docker image
# id: build-and-push
# uses: docker/build-push-action@v4
# with:
# context: .
# file: ${{ env.DOCKERFILE }}
# push: true
# platforms: 'linux/amd64'
# build-args: |
# GIT_SHA=${{ env.GITHUB_SHA }}
# DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
# PLATFORM=${{ env.PLATFORM }}
# tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
# labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
# cache-from: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
# cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
# - name: Final
# id: final
# run: |
# echo "docker_image=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT}}${{ env.LABEL }}" >> "$GITHUB_OUTPUT"
# echo "docker_devices=${{ env.DOCKER_DEVICES }}" >> "$GITHUB_OUTPUT"
# echo "runs_on=${{ env.RUNS_ON }}" >> "$GITHUB_OUTPUT"
# echo "label=${{ env.LABEL }}" >> "$GITHUB_OUTPUT"
# echo "extra_pytest=${{ env.EXTRA_PYTEST }}" >> "$GITHUB_OUTPUT"
build-and-push:
outputs:
docker_image: ${{ steps.final.outputs.docker_image }}
docker_devices: ${{ steps.final.outputs.docker_devices }}
runs_on: ${{ steps.final.outputs.runs_on }}
label: ${{ steps.final.outputs.label }}
extra_pytest: ${{ steps.final.outputs.extra_pytest }}
concurrency:
group: ${{ github.workflow }}-build-and-push-image-${{ inputs.hardware }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
runs-on:
group: aws-highmemory-32-plus-priv
permissions:
contents: write
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1
- name: Construct harware variables
shell: bash
run: |
case ${{ inputs.hardware }} in
cuda)
export dockerfile="Dockerfile"
export label_extension=""
export docker_devices=""
export runs_on="aws-g6-12xl-plus-priv-cache"
export platform=""
export extra_pytest=""
;;
rocm)
export dockerfile="Dockerfile_amd"
export label_extension="-rocm"
export docker_devices="/dev/kfd,/dev/dri"
export runs_on="amd-gpu-runners"
export platform=""
export extra_pytest="-k test_flash_gemma_load"
;;
intel-xpu)
export dockerfile="Dockerfile_intel"
export label_extension="-intel-xpu"
export docker_devices=""
export runs_on="ubuntu-latest"
export platform="xpu"
export extra_pytest=""
;;
intel-cpu)
export dockerfile="Dockerfile_intel"
export label_extension="-intel-cpu"
export docker_devices=""
export runs_on="ubuntu-latest"
export platform="cpu"
export extra_pytest=""
;;
esac
echo $dockerfile
echo "Dockerfile=${dockerfile}"
echo $label_extension
echo $docker_devices
echo $runs_on
echo $platform
echo "DOCKERFILE=${dockerfile}" >> $GITHUB_ENV
echo "LABEL=${label_extension}" >> $GITHUB_ENV
echo "PLATFORM=${platform}" >> $GITHUB_ENV
echo "DOCKER_DEVICES=${docker_devices}" >> $GITHUB_ENV
echo "RUNS_ON=${runs_on}" >> $GITHUB_ENV
echo "EXTRA_PYTEST=${extra_pytest}" >> $GITHUB_ENV
echo REGISTRY_MIRROR=$REGISTRY_MIRROR >> $GITHUB_ENV
- name: Initialize Docker Buildx
uses: docker/setup-buildx-action@v3
with:
install: true
buildkitd-config: /tmp/buildkitd.toml
- name: Login to internal Container Registry
uses: docker/login-action@v3
with:
username: ${{ secrets.REGISTRY_USERNAME }}
password: ${{ secrets.REGISTRY_PASSWORD }}
registry: registry.internal.huggingface.tech
- name: Login to GitHub Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to Azure Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.AZURE_DOCKER_USERNAME }}
password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
# If pull request
- name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name == 'pull_request' }}
id: meta-pr
uses: docker/metadata-action@v5
with:
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
tags: |
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
# If main, release or tag
- name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name != 'pull_request' }}
id: meta
uses: docker/metadata-action@v4.3.0
with:
flavor: |
latest=auto
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
ghcr.io/huggingface/text-generation-inference
db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
tags: |
type=semver,pattern={{version}}${{ env.LABEL }}
type=semver,pattern={{major}}.{{minor}}${{ env.LABEL }}
type=raw,value=latest${{ env.LABEL }},enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
- name: Build and push Docker image
id: build-and-push
uses: docker/build-push-action@v4
with:
context: .
file: ${{ env.DOCKERFILE }}
push: true
platforms: 'linux/amd64'
build-args: |
GIT_SHA=${{ env.GITHUB_SHA }}
DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
PLATFORM=${{ env.PLATFORM }}
tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
cache-from: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
- name: Final
id: final
run: |
echo "docker_image=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT}}${{ env.LABEL }}" >> "$GITHUB_OUTPUT"
echo "docker_devices=${{ env.DOCKER_DEVICES }}" >> "$GITHUB_OUTPUT"
echo "runs_on=${{ env.RUNS_ON }}" >> "$GITHUB_OUTPUT"
echo "label=${{ env.LABEL }}" >> "$GITHUB_OUTPUT"
echo "extra_pytest=${{ env.EXTRA_PYTEST }}" >> "$GITHUB_OUTPUT"
integration_tests:
concurrency:
group: ${{ github.workflow }}-${{ github.job }}-${{ needs.build-and-push.outputs.label }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
# needs: build-and-push
needs: build-and-push
runs-on:
# group: ${{ needs.build-and-push.outputs.runs_on }}
group: amd-gpu-runners
# if: needs.build-and-push.outputs.runs_on != 'ubuntu-latest'
group: ${{ needs.build-and-push.outputs.runs_on }}
if: needs.build-and-push.outputs.runs_on != 'ubuntu-latest'
env:
PYTEST_FLAGS: ${{ (startsWith(github.ref, 'refs/tags/') || github.ref == 'refs/heads/main' || inputs.release-tests == true) && '--release' || '--release' }}
steps:
@ -190,15 +189,9 @@ jobs:
- name: Run tests
run: |
export DOCKER_VOLUME=/mnt2/
# export DOCKER_IMAGE=${{ needs.build-and-push.outputs.docker_image }}
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-318bbc7-rocm
# export DOCKER_DEVICES=${{ needs.build-and-push.outputs.docker_devices }}
export DOCKER_DEVICES=/dev/kfd,/dev/dri
# export EXTRA_PYTEST="${{ needs.build-and-push.outputs.extra_pytest }}"
export DOCKER_IMAGE=${{ needs.build-and-push.outputs.docker_image }}
export DOCKER_DEVICES=${{ needs.build-and-push.outputs.docker_devices }}
export EXTRA_PYTEST="${{ needs.build-and-push.outputs.extra_pytest }}"
export HF_TOKEN=${{ secrets.HF_TOKEN }}
echo $DOCKER_IMAGE
python -c 'import docker; client = docker.from_env(); client.containers.run("registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-318bbc7-rocm", devices=["/dev/kfd", "/dev/dri"], environment={"MODEL_ID": "gpt2", "NUM_SHARD": 2})'
# which pytest
pip freeze
# pytest -s -vv integration-tests -k flash_llama_grammar_tools_auto
# pytest -s -vv integration-tests ${PYTEST_FLAGS} ${EXTRA_PYTEST}
pytest -s -vv integration-tests ${PYTEST_FLAGS} ${EXTRA_PYTEST}