huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Integration tests for intel ?

Browse Source
This commit is contained in:
Nicolas Patry 2024-06-04 23:08:34 +00:00
parent 89fc5c8d33
commit caf8fa0847
1 changed files with 145 additions and 250 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

395
.github/workflows/build.yaml vendored
View File

@ -57,218 +57,130 @@ jobs:
{"Key": "GitHubRepository", "Value": "${{ github.repository }}"} {"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
] ]
build-and-push-image: # build-and-push-image:
concurrency: # concurrency:
group: ${{ github.workflow }}-build-and-push-image-${{ github.head_ref || github.run_id }} # group: ${{ github.workflow }}-build-and-push-image-${{ github.head_ref || github.run_id }}
cancel-in-progress: true # cancel-in-progress: true
needs: start-runner # required to start the main job when the runner is ready # needs: 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 # runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
permissions: # permissions:
contents: write # contents: write
packages: write # packages: write
# This is used to complete the identity challenge # # This is used to complete the identity challenge
# with sigstore/fulcio when running outside of PRs. # # with sigstore/fulcio when running outside of PRs.
id-token: write # id-token: write
security-events: write # security-events: write
steps: # steps:
- name: Checkout repository # - name: Checkout repository
uses: actions/checkout@v3 # uses: actions/checkout@v3
- name: Initialize Docker Buildx # - name: Initialize Docker Buildx
uses: docker/setup-buildx-action@v2.0.0 # uses: docker/setup-buildx-action@v2.0.0
with: # with:
install: true # install: true
- name: Inject slug/short variables # - name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1 # uses: rlespinasse/github-slug-action@v4.4.1
- name: Tailscale # - name: Tailscale
uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966 # uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
with: # with:
authkey: ${{ secrets.TAILSCALE_AUTHKEY }} # authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
- name: Login to GitHub Container Registry # - name: Login to GitHub Container Registry
if: github.event_name != 'pull_request' # if: github.event_name != 'pull_request'
uses: docker/login-action@v2 # uses: docker/login-action@v2
with: # with:
registry: ghcr.io # registry: ghcr.io
username: ${{ github.actor }} # username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }} # password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to internal Container Registry # - name: Login to internal Container Registry
uses: docker/login-action@v2.1.0 # uses: docker/login-action@v2.1.0
with: # with:
username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }} # username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }} # password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
registry: registry.internal.huggingface.tech # registry: registry.internal.huggingface.tech
- name: Login to Azure Container Registry # - name: Login to Azure Container Registry
if: github.event_name != 'pull_request' # if: github.event_name != 'pull_request'
uses: docker/login-action@v2.1.0 # uses: docker/login-action@v2.1.0
with: # with:
username: ${{ secrets.AZURE_DOCKER_USERNAME }} # username: ${{ secrets.AZURE_DOCKER_USERNAME }}
password: ${{ secrets.AZURE_DOCKER_PASSWORD }} # password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io # registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
# If pull request # # If pull request
- name: Extract metadata (tags, labels) for Docker # - name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name == 'pull_request' }} # if: ${{ github.event_name == 'pull_request' }}
id: meta-pr # id: meta-pr
uses: docker/metadata-action@v4.3.0 # uses: docker/metadata-action@v4.3.0
with: # with:
images: | # images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference # registry.internal.huggingface.tech/api-inference/community/text-generation-inference
tags: | # tags: |
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }} # type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
# If main, release or tag # # If main, release or tag
- name: Extract metadata (tags, labels) for Docker # - name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name != 'pull_request' }} # if: ${{ github.event_name != 'pull_request' }}
id: meta # id: meta
uses: docker/metadata-action@v4.3.0 # uses: docker/metadata-action@v4.3.0
with: # with:
flavor: | # flavor: |
latest=auto # latest=auto
images: | # images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference # registry.internal.huggingface.tech/api-inference/community/text-generation-inference
ghcr.io/huggingface/text-generation-inference # ghcr.io/huggingface/text-generation-inference
db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference # db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
tags: | # tags: |
type=semver,pattern={{version}} # type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}} # type=semver,pattern={{major}}.{{minor}}
type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }} # type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }} # type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
- name: Build and push Docker image # - name: Build and push Docker image
id: build-and-push # id: build-and-push
uses: docker/build-push-action@v4 # uses: docker/build-push-action@v4
with: # with:
context: . # context: .
file: Dockerfile # file: Dockerfile
push: true # push: true
platforms: 'linux/amd64' # platforms: 'linux/amd64'
build-args: | # build-args: |
GIT_SHA=${{ env.GITHUB_SHA }} # GIT_SHA=${{ env.GITHUB_SHA }}
DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }} # DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}
tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }} # tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }} # labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min # cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min # cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min
integration-tests: # integration-tests:
concurrency: # concurrency:
group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }} # group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true # cancel-in-progress: true
needs: # needs:
- start-runner # - start-runner
- build-and-push-image # Wait for the docker image to be built # - build-and-push-image # Wait for the docker image to be built
runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner # runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
env: # env:
DOCKER_VOLUME: /cache # DOCKER_VOLUME: /cache
steps: # steps:
- uses: actions/checkout@v2 # - uses: actions/checkout@v2
- name: Inject slug/short variables # - name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1 # uses: rlespinasse/github-slug-action@v4.4.1
- name: Set up Python # - name: Set up Python
uses: actions/setup-python@v4 # uses: actions/setup-python@v4
with: # with:
python-version: 3.9 # python-version: 3.9
- name: Tailscale # - name: Tailscale
uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966 # uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
with: # with:
authkey: ${{ secrets.TAILSCALE_AUTHKEY }} # authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
- name: Prepare disks # - name: Prepare disks
run: | # run: |
sudo mkfs -t ext4 /dev/nvme1n1 # sudo mkfs -t ext4 /dev/nvme1n1
sudo mkdir ${{ env.DOCKER_VOLUME }} # sudo mkdir ${{ env.DOCKER_VOLUME }}
sudo mount /dev/nvme1n1 ${{ env.DOCKER_VOLUME }} # sudo mount /dev/nvme1n1 ${{ env.DOCKER_VOLUME }}
- name: Install # - name: Install
run: | # run: |
make install-integration-tests # make install-integration-tests
- name: Run tests # - name: Run tests
run: | # run: |
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }} # export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}
export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }} # export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
pytest -s -vv integration-tests # pytest -s -vv integration-tests
build-and-push-image-rocm:
concurrency:
group: ${{ github.workflow }}-build-and-push-image-rocm-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
runs-on: intel-pvc-tgi
permissions:
contents: write
packages: write
# This is used to complete the identity challenge
# with sigstore/fulcio when running outside of PRs.
id-token: write
security-events: write
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Initialize Docker Buildx
uses: docker/setup-buildx-action@v2.0.0
with:
install: true
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1
- name: Tailscale
uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
with:
authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
- name: Login to GitHub Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v2
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to internal Container Registry
uses: docker/login-action@v2.1.0
with:
username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
registry: registry.internal.huggingface.tech
- name: Login to Azure Container Registry
if: github.event_name != 'pull_request'
uses: docker/login-action@v2.1.0
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: ${{ github.event_name == 'pull_request' }}
id: meta-pr
uses: docker/metadata-action@v4.3.0
with:
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
tags: |
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
# If main, release or tag
- name: Extract metadata (tags, labels) for Docker
if: ${{ github.event_name != 'pull_request' }}
id: meta
uses: docker/metadata-action@v4.3.0
with:
flavor: |
latest=false
images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference
ghcr.io/huggingface/text-generation-inference
db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
tags: |
type=semver,pattern={{version}}-rocm
type=semver,pattern={{major}}.{{minor}}-rocm
type=raw,value=latest-rocm,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
- name: Build and push Docker image
id: build-and-push
uses: docker/build-push-action@v4
with:
context: .
file: Dockerfile_amd
push: true
platforms: 'linux/amd64'
build-args: |
GIT_SHA=${{ env.GITHUB_SHA }}
DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min
build-and-push-image-intel: build-and-push-image-intel:
concurrency: concurrency:
@ -276,8 +188,6 @@ jobs:
cancel-in-progress: true cancel-in-progress: true
needs: needs:
- start-runner - start-runner
- build-and-push-image # Wait for the main docker image to be built
- integration-tests # Wait for the main integration-tests
runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
permissions: permissions:
contents: write contents: write
@ -364,15 +274,34 @@ jobs:
labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }} labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min
integration-tests-intel:
concurrency:
group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
needs:
- start-runner
- build-and-push-image-intel
runs-on: intel-pvc-tgi
container:
image: registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ needs.build-and-push-image-intel.outputs.short_sha }}-intel
options: --device /dev/kfd --device /dev/dri --env ROCR_VISIBLE_DEVICES --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/cache
env:
DOCKER_VOLUME: /cache
steps:
- name: Install
run: |
make install-integration-tests
- name: Run tests
run: |
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}-intel
export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
pytest -s -vv integration-tests
stop-runner: stop-runner:
name: Stop self-hosted EC2 runner name: Stop self-hosted EC2 runner
needs: needs:
- start-runner - start-runner
- build-and-push-image
- build-and-push-image-rocm
- build-and-push-image-intel - build-and-push-image-intel
- integration-tests
runs-on: ubuntu-latest runs-on: ubuntu-latest
env: env:
AWS_REGION: us-east-1 AWS_REGION: us-east-1
@ -393,37 +322,3 @@ jobs:
ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }} ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}
# TODO: Move this to `build_amd.yml` (and `build_nvidia.yml`) # TODO: Move this to `build_amd.yml` (and `build_nvidia.yml`)
# integration-tests-rocm:
# concurrency:
# group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
# cancel-in-progress: true
# needs:
# - start-runner
# - build-and-push-image
# - integration-tests
# - build-and-push-image-rocm
# - stop-runner
# runs-on: [self-hosted, amd-gpu, multi-gpu, mi300]
# container:
# image: registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ needs.build-and-push-image-rocm.outputs.short_sha }}-rocm
# options: --device /dev/kfd --device /dev/dri --env ROCR_VISIBLE_DEVICES --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/cache
# env:
# DOCKER_VOLUME: /cache
# steps:
# - name: ROCM-SMI
# run: |
# rocm-smi
# - name: ROCM-INFO
# run: |
# rocminfo | grep "Agent" -A 14
# - name: Show ROCR environment
# run: |
# echo "ROCR: $ROCR_VISIBLE_DEVICES"
# - name: Install
# run: |
# make install-integration-tests
# - name: Run tests
# run: |
# export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
# pytest -s -vv integration-tests