Let's iterate a bit faster.

This commit is contained in:
Nicolas Patry 2024-06-07 09:50:43 +02:00
parent 97af55b7ef
commit c8128c794d

View File

@ -24,129 +24,129 @@ on:
- 'main' - 'main'
jobs: jobs:
build-and-push-image: # build-and-push-image:
concurrency: # concurrency:
group: ${{ github.workflow }}-build-and-push-image-${{ matrix.name }}-${{ github.head_ref || github.run_id }} # group: ${{ github.workflow }}-build-and-push-image-${{ matrix.name }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true # cancel-in-progress: true
runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci] # runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci]
strategy: # strategy:
matrix: # matrix:
include: # include:
- name: "cuda" # - name: "cuda"
label: "" # label: ""
dockerfile: "Dockerfile" # dockerfile: "Dockerfile"
- name: "amd" # - name: "amd"
label: "-rocm" # label: "-rocm"
dockerfile: "Dockerfile_amd" # dockerfile: "Dockerfile_amd"
- name: "intel" # - name: "intel"
label: "-intel" # label: "-intel"
dockerfile: "Dockerfile_intel" # dockerfile: "Dockerfile_intel"
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: huggingface/tailscale-action@main # uses: huggingface/tailscale-action@main
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 }}${{ matrix.label }} # type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ matrix.label }}
# 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: ${{ github.event_name != 'pull_request' }}
id: meta # id: meta
uses: docker/metadata-action@v4.3.0 # uses: docker/metadata-action@v4.3.0
with: # with:
flavor: | # flavor: |
latest=auto # latest=auto
images: | # images: |
registry.internal.huggingface.tech/api-inference/community/text-generation-inference # registry.internal.huggingface.tech/api-inference/community/text-generation-inference
ghcr.io/huggingface/text-generation-inference # ghcr.io/huggingface/text-generation-inference
db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference # db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
tags: | # tags: |
type=semver,pattern={{version}}${{ matrix.label }} # type=semver,pattern={{version}}${{ matrix.label }}
type=semver,pattern={{major}}.{{minor}}${{ matrix.label }} # type=semver,pattern={{major}}.{{minor}}${{ matrix.label }}
type=raw,value=latest${{ matrix.label }},enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }} # type=raw,value=latest${{ matrix.label }},enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ matrix.label }} # type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ matrix.label }}
- 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: ${{ matrix.dockerfile }} # file: ${{ matrix.dockerfile }}
push: true # push: true
platforms: 'linux/amd64' # platforms: 'linux/amd64'
build-args: | # build-args: |
GIT_SHA=${{ env.GITHUB_SHA }} # GIT_SHA=${{ env.GITHUB_SHA }}
DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}${{ matrix.label }} # DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}${{ matrix.label }}
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: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache${{ matrix.label }},mode=min # cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache${{ matrix.label }},mode=min
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache${{ matrix.label }},mode=min # cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache${{ matrix.label }},mode=min
integration-tests-cuda: # integration-tests-cuda:
concurrency: # concurrency:
group: ${{ github.workflow }}-${{ github.job }}-cuda-${{ github.head_ref || github.run_id }} # group: ${{ github.workflow }}-${{ github.job }}-cuda-${{ github.head_ref || github.run_id }}
cancel-in-progress: true # cancel-in-progress: true
runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci] # runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci]
needs: build-and-push-image # needs: build-and-push-image
steps: # steps:
- name: Checkout repository # - name: Checkout repository
uses: actions/checkout@v4 # uses: actions/checkout@v4
- name: Inject slug/short variables # - name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4.4.1 # uses: rlespinasse/github-slug-action@v4.4.1
- name: Set up Python # - name: Set up Python
uses: actions/setup-python@v4 # uses: actions/setup-python@v4
with: # with:
python-version: 3.9 # python-version: 3.9
- name: Install # - name: Install
run: | # run: |
make install-integration-tests # make install-integration-tests
- name: Run tests # - name: Run tests
run: | # run: |
export DOCKER_VOLUME=/mnt/cache # export DOCKER_VOLUME=/mnt/cache
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ 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
integration-tests-rocm: integration-tests-rocm:
concurrency: concurrency:
group: ${{ github.workflow }}-${{ github.job }}-rocm-${{ github.head_ref || github.run_id }} group: ${{ github.workflow }}-${{ github.job }}-rocm-${{ github.head_ref || github.run_id }}
@ -175,6 +175,7 @@ jobs:
- name: Run tests - name: Run tests
run: | run: |
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }} export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}
export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-025f40a-rocm
export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }} export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
export DOCKER_DEVICES=/dev/kfd,/dev/dri export DOCKER_DEVICES=/dev/kfd,/dev/dri
python -m pytest -s -vv integration-tests/models/test_flash_gpt2.py python -m pytest -s -vv integration-tests/models/test_flash_gpt2.py