Merge branch 'main' into am/click-cli

Author: amaslenn

.github/workflows/ci.yml

@@ -18,7 +18,7 @@ jobs:
         uses: actions/setup-python@v5
 
       - name: Install dependencies
-        run: pip install '.[dev]'
+        run: pip install '.[dev,docs]'
 
       - name: Run ruff linter
         run: ruff check
@@ -42,6 +42,14 @@ jobs:
 
           taplo fmt --check --diff
 
+      - name: Build documentation
+        run: |
+          set -eE
+          set -o pipefail
+
+          cd doc
+          make html
+
   test:
     name: Run pytest
 

.github/workflows/docs.yml

@@ -0,0 +1,66 @@
+name: Build and Deploy Documentation
+
+on:
+  push:
+    branches: [ main ]
+  workflow_dispatch:    # Allow manual triggering
+
+# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
+# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+      with:
+        enable-cache: true
+
+    - name: Set up environment
+      run: |
+        set -eE
+        set -o pipefail
+
+        uv sync --extra docs
+
+    - name: Build documentation
+      run: |
+        set -eE
+        set -o pipefail
+
+        source .venv/bin/activate
+        cd doc
+        make html
+
+    - name: Add .nojekyll file
+      run: touch doc/_build/html/.nojekyll
+
+    - name: Upload artifact
+      uses: actions/upload-pages-artifact@v3
+      with:
+        path: ./doc/_build/html
+
+  deploy:
+    name: Deploy to GitHub Pages
+    needs: build
+
+    permissions:
+      pages: write
+      id-token: write
+
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+
+    runs-on: ubuntu-latest
+    steps:
+    - name: Deploy to GitHub Pages
+      id: deployment
+      uses: actions/deploy-pages@v4

.gitignore

@@ -21,6 +21,7 @@ share/python-wheels/
 *.egg-info/
 .installed.cfg
 *.egg
+doc/_build
 
 # PyInstaller
 # Usually these files are written by a python script from a template

README.md

@@ -54,6 +54,8 @@ These schemas enable CloudAI to be flexible and compatible with different system
 |SlurmContainer|✅|❌|❌|❌|
 |MegatronRun (experimental)|✅|❌|❌|❌|
 
+For more detailed information, please refer to the [official documentation](https://nvidia.github.io/cloudai/workloads/index.html).
+
 ## Details
 ###  Set Up Access to the Private NGC Registry
 First, ensure you have access to the Docker repository. Follow the following steps:
@@ -149,11 +151,11 @@ cloudai verify-configs conf/common/system/example_slurm_cluster.toml
 cloudai verify-configs --tests-dir conf/release/spcx/l40s/test conf/release/spcx/l40s/test_scenario
 ```
 
+## Additional Documentation
+For more detailed instructions and guidance, including advanced usage and troubleshooting, please refer to the [official documentation](https://nvidia.github.io/cloudai/).
+
 ## Contribution
 Please feel free to contribute to the CloudAI project and share your insights. Your contributions are highly appreciated.
 
 ## License
 This project is licensed under Apache 2.0. See the LICENSE file for detailed information.
-
-## Additional Documentation
-For more detailed instructions and guidance, including advanced usage and troubleshooting, please refer to the [USER_GUIDE.md](./USER_GUIDE.md)

conf/common/test/llama2_70b.toml

@@ -0,0 +1,14 @@
+# Minimal makefile for Sphinx documentation
+
+SPHINXOPTS    ?=
+SPHINXBUILD  ?= sphinx-build
+SOURCEDIR    = .
+BUILDDIR     = _build
+
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)