init docs structure (#234)

Signed-off-by: Siddhant Ray <[email protected]>

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/requirements-docs.txt

@@ -0,0 +1,8 @@
+sphinx==8.0.2
+sphinx-autodoc-typehints==2.4.1
+sphinx-book-theme==1.1.3
+sphinx-click==6.0.0
+sphinx-copybutton==0.5.2
+sphinx-togglebutton==0.3.2
+sphinx_design==0.6.1
+sphinxemoji==0.3.1

docs/source/benchmarks/multiround-qa.rst

@@ -0,0 +1,4 @@
+.. _multiround-qa:
+
+Multi-round QA
+==============

docs/source/conf.py

@@ -0,0 +1,96 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+import os
+import sys
+from dataclasses import asdict
+
+from sphinx.ext import autodoc
+
+sys.path.insert(0, os.path.abspath("../../src"))
+
+project = "production-stack"
+copyright = "2025, vLLM Production Stack Team"
+author = "vLLM Production Stack Team"
+
+extensions = [
+    "sphinx.ext.napoleon",
+    "sphinx.ext.linkcode",
+    "sphinx.ext.intersphinx",
+    "sphinx_copybutton",
+    "sphinx.ext.autodoc",
+    "sphinx.ext.autosummary",
+    "myst_parser",
+    "sphinxarg.ext",
+    "sphinx_design",
+    "sphinx_togglebutton",
+]
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = []
+
+templates_path = ["_templates"]
+exclude_patterns = []
+
+
+class MockedClassDocumenter(autodoc.ClassDocumenter):
+    """Remove note about base class when a class is
+    derived from object."""
+
+    def add_line(self, line: str, source: str, *lineno: int) -> None:
+        if line == "   Bases: :py:class:`object`":
+            return
+        super().add_line(line, source, *lineno)
+
+
+autodoc.ClassDocumenter = MockedClassDocumenter
+
+# autodoc_default_options = {
+#     "members": True,
+#     "undoc-members": True,
+#     "private-members": True
+# }
+
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_title = project
+html_theme = "sphinx_book_theme"
+html_static_path = ["_static"]
+html_logo = "./assets/prodstack_icon.png"
+html_favicon = "./assets/output.ico"
+html_permalinks_icon = "<span>#</span>"
+# pygments_style = "sphinx"
+# pygments_style_dark = "fruity"
+html_theme_options = {
+    "path_to_docs": "docs/source",
+    "repository_url": "https://github.com/vllm-project/production-stack",
+    "use_repository_button": True,
+    "use_edit_page_button": True,
+    # navigation and sidebar
+    "show_toc_level": 2,
+    "announcement": None,
+    "secondary_sidebar_items": [
+        "page-toc",
+    ],
+    "navigation_depth": 3,
+    "primary_sidebar_end": [],
+    "pygments_light_style": "tango",
+    "pygments_dark_style": "monokai",
+}
+
+intersphinx_mapping = {
+    "python": ("https://docs.python.org/3", None),
+    "typing_extensions": ("https://typing-extensions.readthedocs.io/en/latest", None),
+    "numpy": ("https://numpy.org/doc/stable", None),
+    "torch": ("https://pytorch.org/docs/stable", None),
+    "psutil": ("https://psutil.readthedocs.io/en/stable", None),
+}

docs/source/deployment/cloud-deployment/aws.rst

@@ -0,0 +1,4 @@
+.. _aws:
+
+AWS
+===

docs/source/deployment/cloud-deployment/gcp.rst

@@ -0,0 +1,4 @@
+.. _gcp:
+
+Google Cloud Platform
+=====================

docs/source/deployment/cloud-deployment/index.rst

@@ -0,0 +1,14 @@
+.. _index:
+
+
+Cloud Environments
+==============================================
+
+📈 Easily deploy the stack on AWS, GCP, or any other cloud provider
+
+.. toctree::
+    :maxdepth: 1
+    :caption: Deployment
+
+    aws.rst
+    gcp.rst

docs/source/deployment/helm.rst

@@ -0,0 +1,4 @@
+.. _helm_charts:
+
+Helm Charts
+=======================================

docs/source/deployment/ray/ray.rst

@@ -0,0 +1,4 @@
+.. _ray_deploy:
+
+Ray Deployment
+=======================================

docs/source/dev_guide/dev_api/engine-stats.rst

@@ -0,0 +1,4 @@
+.. _engine-stats:
+
+Engine Stats
+============

docs/source/dev_guide/dev_api/index.rst

@@ -0,0 +1,12 @@
+.. _dev_api_index:
+
+Developer API
+================
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Developer Guide
+
+   router-logic.rst
+   engine-stats.rst
+   service-discovery.rst

docs/source/dev_guide/dev_api/router-logic.rst

@@ -0,0 +1,4 @@
+.. _router-logic:
+
+Router Logic
+============

docs/source/dev_guide/dev_api/service-discovery.rst

@@ -0,0 +1,4 @@
+.. _service-discovery:
+
+Service Discovery
+=================

docs/source/dev_guide/peripheral/index.rst

@@ -0,0 +1,11 @@
+.. _peripheral_index:
+
+Peripheral
+================
+
+.. toctree::
+    :maxdepth: 1
+    :caption: Developer Guide
+
+    models.rst
+    interfaces.rst

docs/source/dev_guide/peripheral/interfaces.rst

@@ -0,0 +1,4 @@
+.. _dev_interfaces:
+
+Interfaces
+================

docs/source/dev_guide/peripheral/models.rst

@@ -0,0 +1,4 @@
+.. _models:
+
+Models
+======

docs/source/getting_started/examples.rst

@@ -0,0 +1,6 @@
+.. _examples:
+
+Minimal Example
+===============
+
+Add simple tutorial here.

docs/source/getting_started/installation.rst

@@ -0,0 +1,59 @@
+.. _installation:
+
+.. role:: raw-html(raw)
+    :format: html
+
+Installation
+============
+
+Architecture
+------------
+
+.. figure:: ../assets/prodarch.png
+  :width: 60%
+  :align: center
+  :alt: production-arch
+  :class: no-scaled-link
+
+
+The stack is set up using Helm, and contains the following key parts:
+
+
+    * **Serving engine**: The vLLM engines that run different LLMs
+    * **Request router**: Directs requests to appropriate backends based on routing keys or session IDs to maximize KV cache reuse.
+    * **Observability stack**: monitors the metrics of the backends through `Prometheus <https://prometheus.io/>`_ and `Grafana <https://grafana.com/>`_.
+
+
+Prerequisites
+-------------
+
+- A running Kubernetes (K8s) environment with GPUs
+- Run ``cd utils`` && ``bash install-minikube-cluster.sh``
+- Or follow our `tutorial <https://github.com/vllm-project/production-stack/blob/main/tutorials/00-install-kubernetes-env.md>`_
+
+
+Deployment
+----------
+
+vLLM Production Stack can be deployed via helm charts. Clone the repo to local and execute the following commands for a minimal deployment:
+
+.. code:: bash
+
+    git clone https://github.com/vllm-project/production-stack.git
+    cd production-stack/
+    helm repo add vllm https://vllm-project.github.io/production-stack
+    helm install vllm vllm/vllm-stack -f tutorials/assets/values-01-minimal-example.yaml
+
+
+The deployed stack provides the same `OpenAI API interface <https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html?ref=blog.mozilla.ai#openai-compatible-server>`_ as vLLM, and can be accessed through kubernetes service.
+
+To validate the installation and and send query to the stack, refer to this `example <https://github.com/vllm-project/production-stack/blob/main/tutorials/01-minimal-helm-installation.md>`_.
+
+Uninstallation
+--------------
+
+To uninstall the stack, run:
+
+.. code:: bash
+
+    sudo helm uninstall vllm

docs/source/getting_started/troubleshooting.rst

@@ -0,0 +1,4 @@
+.. _troubleshooting:
+
+Troubleshooting
+===========================