.. production-stack documentation master file, created by sphinx-quickstart on Mon Mar 3 12:36:28 2025. You can adapt this file completely to your liking, but it should at least contain the root toctree directive.

.. role:: raw-html(raw) :format: html

Welcome to production-stack!

.. figure:: ./assets/prodstack.png :width: 60% :align: center :alt: production-stack :class: no-scaled-link

.. raw:: html

K8S-native cluster-wide deployment for vLLM.

.. raw:: html

Star Watch Fork

vLLM Production Stack project provides a reference implementation on how to build an inference stack on top of vLLM, which allows you to:

  • 🚀 Scale from single vLLM instance to distributed vLLM deployment without changing any application code
  • 💻 Monitor the metrics through a web dashboard
  • 😄 Enjoy the performance benefits brought by request routing and KV cache offloading
  • 📈 Easily deploy the stack on AWS, GCP, or any other cloud provider

Documentation

.. Add your content using reStructuredText syntax. See the .. reStructuredText .. documentation for details.

.. toctree:: :maxdepth: 2 :caption: Getting Started

getting_started/prerequisite getting_started/quickstart getting_started/faq

.. toctree:: :maxdepth: 2 :caption: Deployment

deployment/index

.. toctree:: :maxdepth: 2 :caption: Use Cases

use_cases/kv-cache-aware-routing use_cases/prefix-aware-routing use_cases/disaggregated-prefill use_cases/sharing-kv-cache use_cases/benchmarking use_cases/distributed-tracing use_cases/tool-enabled-installation use_cases/pipeline-parallelism-kuberay use_cases/sleep-wakeup-mode use_cases/autoscaling-keda use_cases/semantic-router-integration

.. toctree:: :maxdepth: 2 :caption: Developer Guide

developer_guide/contributing developer_guide/docker

.. toctree:: :maxdepth: 2 :caption: Community

community/meetings