For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Digest
  • Getting Started
    • Quickstart
    • Installation
    • Support Matrix
    • Feature Matrix
    • Examples
  • Kubernetes Deployment
  • User Guides
    • Tool Calling
    • Multimodality Support
    • Finding Best Initial Configs
    • Dynamo Benchmarking Guide
    • Tuning Disaggregated Performance
    • Writing Python Workers in Dynamo
    • Glossary
  • Components
    • Router
  • Design Docs
    • Overall Architecture
    • Architecture Flow
    • Disaggregated Serving
    • Distributed Runtime
NVIDIANVIDIA
Developer-friendly docs for your API
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2026, NVIDIA Corporation.

LogoLogoDocumentation
Digest
On this page
  • Prerequisites
  • Install Rust and Cargo using rustup:
  • Build
  • Start Dependencies
  • Docker Compose
  • Local (alternate)
  • Run Examples
  • Rust hello_world
  • Python
User Guides

Dynamo Runtime

||View as Markdown|
Previous

Disaggregation and Performance Tuning

Next

Dynamo Observability

A Datacenter Scale Distributed Inference Serving Framework

License

Rust implementation of the Dynamo runtime system, enabling distributed computing capabilities for machine learning workloads.

Prerequisites

Install Rust and Cargo using rustup:

$curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

Build

cargo build
cargo test

Start Dependencies

Docker Compose

The simplest way to deploy the pre-requisite services is using docker-compose, defined in deploy/docker-compose.yml.

# At the root of the repository:
docker compose -f deploy/docker-compose.yml up -d

This will deploy a NATS.io server and an etcd server used to communicate between and discover components at runtime.

Local (alternate)

To deploy the pre-requisite services locally instead of using docker-compose above, you can manually launch each:

  • NATS.io server with Jetstream
    • example: nats-server -js --trace
  • etcd server
    • follow instructions in etcd installation to start an etcd-server locally

Run Examples

When developing or running examples, any process or user that shared your core-services (etcd and nats.io) will be operating within your distributed runtime.

The current examples use a hard-coded namespace. We will address the namespace collisions later.

Most examples require etcd for service discovery. nats.io is required for KV-aware routing with event tracking; for approximate mode (--no-kv-events), NATS is optional.

Rust hello_world

With two terminals open, in one window:

cd examples/hello_world
cargo run --bin server

In the second terminal, execute:

cd examples/hello_world
cargo run --bin client

which should yield some output similar to:

Finished `dev` profile [unoptimized + debuginfo] target(s) in 6.25s
Running `target/debug/client`
Annotated { data: Some("h"), id: None, event: None, comment: None }
Annotated { data: Some("e"), id: None, event: None, comment: None }
Annotated { data: Some("l"), id: None, event: None, comment: None }
Annotated { data: Some("l"), id: None, event: None, comment: None }
Annotated { data: Some("o"), id: None, event: None, comment: None }
Annotated { data: Some(" "), id: None, event: None, comment: None }
Annotated { data: Some("w"), id: None, event: None, comment: None }
Annotated { data: Some("o"), id: None, event: None, comment: None }
Annotated { data: Some("r"), id: None, event: None, comment: None }
Annotated { data: Some("l"), id: None, event: None, comment: None }
Annotated { data: Some("d"), id: None, event: None, comment: None }

Python

See the README.md for details

The Python and Rust hello_world client and server examples are interchangeable, so you can start the Python server.py and talk to it from the Rust client.