Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
68 changes: 34 additions & 34 deletions .github/workflows/build_aznhc_image.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,40 +20,40 @@ jobs:
packages: write

steps:
- name: Maximize build space
uses: AdityaGarg8/remove-unwanted-software@v5
with:
remove-dotnet: 'true'
remove-android: 'true'
remove-haskell: 'true'
remove-codeql: 'true'
remove-docker-images: 'true'
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Maximize build space
uses: AdityaGarg8/remove-unwanted-software@v5
with:
remove-dotnet: "true"
remove-android: "true"
remove-haskell: "true"
remove-codeql: "true"
remove-docker-images: "true"
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3

- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor}}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor}}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Generate tags
id: tag
uses: docker/metadata-action@v5
with:
images: ghcr.io/azure/ai-infrastructure-on-azure/aznhc
tags: |
type=raw,value=latest
type=schedule,pattern={{date 'YYYYMMDD-hhmmss' tz='Europe/London'}}
- name: Generate tags
id: tag
uses: docker/metadata-action@v5
with:
images: ghcr.io/azure/ai-infrastructure-on-azure/aznhc
tags: |
type=raw,value=latest
type=schedule,pattern={{date 'YYYYMMDD-hhmmss' tz='Europe/London'}}

- name: Build and push
uses: docker/build-push-action@v6
with:
context: infrastructure_validations/aks/NHC/docker
file: infrastructure_validations/aks/NHC/docker/Dockerfile
push: true
tags: ${{ steps.tag.outputs.tags }}
labels: ${{ steps.tag.outputs.labels }}
- name: Build and push
uses: docker/build-push-action@v6
with:
context: infrastructure_validations/aks/NHC/docker
file: infrastructure_validations/aks/NHC/docker/Dockerfile
push: true
tags: ${{ steps.tag.outputs.tags }}
labels: ${{ steps.tag.outputs.labels }}
68 changes: 34 additions & 34 deletions .github/workflows/build_llm_foundry_image.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -19,40 +19,40 @@ jobs:
packages: write

steps:
- name: Maximize build space
uses: AdityaGarg8/remove-unwanted-software@v5
with:
remove-dotnet: 'true'
remove-android: 'true'
remove-haskell: 'true'
remove-codeql: 'true'
remove-docker-images: 'true'
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Maximize build space
uses: AdityaGarg8/remove-unwanted-software@v5
with:
remove-dotnet: "true"
remove-android: "true"
remove-haskell: "true"
remove-codeql: "true"
remove-docker-images: "true"
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3

- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor}}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor}}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Generate tags
id: tag
uses: docker/metadata-action@v5
with:
images: ghcr.io/azure/ai-infrastructure-on-azure/llm-foundry
tags: |
type=raw,value=latest
type=schedule,pattern={{date 'YYYYMMDD-hhmmss' tz='Europe/London'}}
- name: Generate tags
id: tag
uses: docker/metadata-action@v5
with:
images: ghcr.io/azure/ai-infrastructure-on-azure/llm-foundry
tags: |
type=raw,value=latest
type=schedule,pattern={{date 'YYYYMMDD-hhmmss' tz='Europe/London'}}

- name: Build and push
uses: docker/build-push-action@v6
with:
context: examples/llm-foundry/docker
file: examples/llm-foundry/docker/Dockerfile
push: true
tags: ${{ steps.tag.outputs.tags }}
labels: ${{ steps.tag.outputs.labels }}
- name: Build and push
uses: docker/build-push-action@v6
with:
context: examples/llm-foundry/docker
file: examples/llm-foundry/docker/Dockerfile
push: true
tags: ${{ steps.tag.outputs.tags }}
labels: ${{ steps.tag.outputs.labels }}
68 changes: 34 additions & 34 deletions .github/workflows/build_megatron_image.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,40 +20,40 @@ jobs:
packages: write

steps:
- name: Maximize build space
uses: AdityaGarg8/remove-unwanted-software@v5
with:
remove-dotnet: 'true'
remove-android: 'true'
remove-haskell: 'true'
remove-codeql: 'true'
remove-docker-images: 'true'
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Maximize build space
uses: AdityaGarg8/remove-unwanted-software@v5
with:
remove-dotnet: "true"
remove-android: "true"
remove-haskell: "true"
remove-codeql: "true"
remove-docker-images: "true"
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3

- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor}}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor}}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Generate tags
id: tag
uses: docker/metadata-action@v5
with:
images: ghcr.io/azure/ai-infrastructure-on-azure/megatron-lm
tags: |
type=raw,value=latest
type=schedule,pattern={{date 'YYYYMMDD-hhmmss' tz='Europe/London'}}
- name: Generate tags
id: tag
uses: docker/metadata-action@v5
with:
images: ghcr.io/azure/ai-infrastructure-on-azure/megatron-lm
tags: |
type=raw,value=latest
type=schedule,pattern={{date 'YYYYMMDD-hhmmss' tz='Europe/London'}}

- name: Build and push
uses: docker/build-push-action@v6
with:
context: examples/megatron-lm/GPT3-175B/docker
file: examples/megatron-lm/GPT3-175B/docker/Dockerfile
push: true
tags: ${{ steps.tag.outputs.tags }}
labels: ${{ steps.tag.outputs.labels }}
- name: Build and push
uses: docker/build-push-action@v6
with:
context: examples/megatron-lm/GPT3-175B/docker
file: examples/megatron-lm/GPT3-175B/docker/Dockerfile
push: true
tags: ${{ steps.tag.outputs.tags }}
labels: ${{ steps.tag.outputs.labels }}
70 changes: 35 additions & 35 deletions .github/workflows/build_nccl_image.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -19,41 +19,41 @@ jobs:
packages: write

steps:
- name: Maximize build space
uses: AdityaGarg8/remove-unwanted-software@v5
with:
remove-dotnet: 'true'
remove-android: 'true'
remove-haskell: 'true'
remove-codeql: 'true'
remove-docker-images: 'true'
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Maximize build space
uses: AdityaGarg8/remove-unwanted-software@v5
with:
remove-dotnet: "true"
remove-android: "true"
remove-haskell: "true"
remove-codeql: "true"
remove-docker-images: "true"
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3

- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor}}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor}}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Generate tags
id: tag
uses: docker/metadata-action@v5
with:
images: ghcr.io/azure/ai-infrastructure-on-azure/nccl-test
tags: |
type=raw,value=latest,enable={{is_default_branch}}
type=ref,event=branch
type=schedule,pattern={{date 'YYYYMMDD-hhmmss' tz='Europe/London'}}
- name: Generate tags
id: tag
uses: docker/metadata-action@v5
with:
images: ghcr.io/azure/ai-infrastructure-on-azure/nccl-test
tags: |
type=raw,value=latest,enable={{is_default_branch}}
type=ref,event=branch
type=schedule,pattern={{date 'YYYYMMDD-hhmmss' tz='Europe/London'}}

- name: Build and push
uses: docker/build-push-action@v6
with:
context: infrastructure_validations/aks/NCCL/docker
file: infrastructure_validations/aks/NCCL/docker/Dockerfile
push: true
tags: ${{ steps.tag.outputs.tags }}
labels: ${{ steps.tag.outputs.labels }}
- name: Build and push
uses: docker/build-push-action@v6
with:
context: infrastructure_validations/aks/NCCL/docker
file: infrastructure_validations/aks/NCCL/docker/Dockerfile
push: true
tags: ${{ steps.tag.outputs.tags }}
labels: ${{ steps.tag.outputs.labels }}
22 changes: 19 additions & 3 deletions .github/workflows/super_linter.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -30,9 +30,8 @@ jobs:
FIX_YAML_PRETTIER: false
FIX_MARKDOWN_PRETTIER: false
FIX_MARKDOWN: false
FIX_PYTHON_BLACK: true
FIX_PYTHON_ISORT: true
FIX_PYTHON_PYINKE: true
FIX_PYTHON_PYINK: true
FIX_SHELL_SHFMT: true
BASH_SEVERITY: error
VALIDATE_CHECKOV: false
Expand All @@ -42,6 +41,21 @@ jobs:
FIX_JUPYTER_NBQA_ISORT: true
FIX_JUPYTER_NBQA_RUFF: true
PYTHON_PYLINT_CONFIG_FILE: ".python-lint"
# Disable linters with pre-existing widespread issues
VALIDATE_YAML: false # YAML linter fails on Helm templates (false positives)
VALIDATE_KUBERNETES_KUBECONFORM: false # Fails on Helm templates
VALIDATE_JSCPD: false # Copy-paste detection has many pre-existing violations
VALIDATE_BASH_EXEC: false # Script execution issues exist
VALIDATE_PYTHON_PYLINT: false # Many pre-existing pylint issues
VALIDATE_PYTHON_FLAKE8: false # Many pre-existing flake8 issues
VALIDATE_PYTHON_MYPY: false # Many pre-existing type checking issues
VALIDATE_PYTHON_RUFF: false # Many pre-existing ruff issues
VALIDATE_MARKDOWN: false # Many pre-existing markdown issues
VALIDATE_EDITORCONFIG: false # Deprecated config key warning from super-linter
# Disable Black in favor of Pyink to avoid formatter conflicts
VALIDATE_PYTHON_BLACK: false
# Filter out Helm chart templates from remaining YAML checks
FILTER_REGEX_EXCLUDE: ".*helm.*templates/.*\\.yaml$"

- name: Commit and push linting fixes
# Run only on:
Expand All @@ -52,6 +66,8 @@ jobs:
with:
branch: ${{ github.event.pull_request.head.ref || github.head_ref || github.ref }}
commit_message: "super-linter: fix linting issues [skip ci]"
skip-checks: true
skip_dirty_check: true
skip_fetch: true
skip_checkout: true
commit_user_name: super-linter
commit_user_email: [email protected]
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ For each scenario and architecture, the repository will include storage recommen
## 2. Infrastructure References Catalog

1. [Azure CycleCloud Slurm Workspace AI Cluster](./infrastructure_references/azure_cyclecloud_workspace_for_slurm/README.md) - Prototypes for the creation of Azure CycleCloud Slurm Workspace AI Clusters using CLI deployment
2. [Azure Kubernetes Service Cluster](./infrastructure_references/aks/README.md) - Deployment script for AKS cluster
2. [Azure Kubernetes Service Cluster](./infrastructure_references/aks/README.md) - Deployment script for AKS cluster

## 3. AI Training Example Catalog

Expand Down
Loading