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
    • Introduction
    • Local Installation
    • Building from Source
    • Contribution Guide
  • Resources
    • Support Matrix
    • Feature Matrix
    • Release Artifacts
    • Examples
  • Kubernetes Deployment
    • Deployment Guide
  • User Guides
    • KV Cache Aware Routing
    • Disaggregated Serving
    • KV Cache Offloading
    • Dynamo Benchmarking
    • Multimodal
    • Diffusion (Preview)
    • Tool Calling
    • LoRA Adapters
    • Agents
    • Observability (Local)
    • Fault Tolerance
    • Writing Python Workers
  • Backends
    • SGLang
    • TensorRT-LLM
    • vLLM
  • Components
    • Frontend
    • Router
    • Planner
    • Profiler
    • KVBM
  • Integrations
    • LMCache
    • SGLang HiCache
    • FlexKV
    • KV Events for Custom Engines
  • Design Docs
    • Overall Architecture
    • Architecture Flow
    • Disaggregated Serving
    • Distributed Runtime
    • Blog
  • Documentation
    • Dynamo Docs Guide
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
  • At a Glance
  • Backend Dependencies
  • Version Labels
  • Version Compatibility
  • CUDA and Driver Requirements
  • CUDA Compatibility Resources
  • Hardware Compatibility
  • GPU Compatibility
  • Platform Architecture Compatibility
  • Cloud Service Provider Compatibility
  • AWS
  • Build Support
Resources

Support Matrix

Hardware, software, and build compatibility for Dynamo
||View as Markdown|
Edit this page
Previous

Contribution Guide

Next

Feature Matrix

See also: Release Artifacts for container images, wheels, Helm charts, and crates | Feature Matrix for backend feature support

At a Glance

Latest stable release: v1.0.0 — SGLang 0.5.9 | TensorRT-LLM 1.3.0rc5.post1 | vLLM 0.16.0 | NIXL 0.10.1

RequirementSupported
GPUNVIDIA Ampere, Ada Lovelace, Hopper, Blackwell
OSUbuntu 22.04, Ubuntu 24.04, CentOS Stream 9 (experimental)
Archx86_64, ARM64 (ARM64 requires Ubuntu 24.04)
CUDA 12Container images for SGLang and vLLM (CUDA 12.9)
CUDA 13Container images for TensorRT-LLM (CUDA 13.1), SGLang and vLLM (CUDA 13.0)

On this page: Backend Dependencies | CUDA and Drivers | Hardware | Platform | Cloud | Build Support

Backend Dependencies

The following table shows the backend framework versions included with each Dynamo release:

DynamoSGLangTensorRT-LLMvLLMNIXL
main (ToT)0.5.91.3.0rc70.17.10.10.1
v1.0.00.5.91.3.0rc5.post10.16.00.10.1
v0.9.10.5.81.3.0rc30.14.10.9.0
v0.9.00.5.81.3.0rc10.14.10.9.0
v0.8.1.post30.5.6.post21.2.0rc6.post30.12.00.8.0
v0.8.1.post20.5.6.post21.2.0rc6.post20.12.00.8.0
v0.8.1.post10.5.6.post21.2.0rc6.post10.12.00.8.0
v0.8.10.5.6.post21.2.0rc6.post10.12.00.8.0
v0.8.00.5.6.post21.2.0rc6.post10.12.00.8.0
v0.7.10.5.4.post31.2.0rc30.11.00.8.0
v0.7.0.post10.5.4.post31.2.0rc30.11.00.8.0
v0.7.00.5.4.post31.2.0rc20.11.00.8.0
v0.6.1.post10.5.3.post21.1.0rc50.11.00.6.0
v0.6.10.5.3.post21.1.0rc50.11.00.6.0
v0.6.00.5.3.post21.1.0rc50.11.00.6.0

Version Labels

  • main (ToT) reflects the current development branch.
  • Releases marked (in progress) or (planned) show target versions that may change before final release.

Version Compatibility

  • Backend versions listed are the only versions tested and supported for each release.
  • TensorRT-LLM does not support Python 3.11; installation of the ai-dynamo[trtllm] wheel will fail on Python 3.11.

CUDA and Driver Requirements

Dynamo container images include CUDA toolkit libraries. The host machine must have a compatible NVIDIA GPU driver installed.

Dynamo VersionBackendCUDA ToolkitMin DriverNotes
1.0.0SGLang12.9575.xx+
13.0580.xx+
TensorRT-LLM13.1580.xx+
vLLM12.9575.xx+
13.0580.xx+
0.9.1SGLang12.9575.xx+
TensorRT-LLM13.0580.xx+
vLLM12.9575.xx+
0.9.0SGLang12.9575.xx+
TensorRT-LLM13.0580.xx+
vLLM12.9575.xx+
0.8.1SGLang12.9575.xx+
13.0580.xx+Experimental
TensorRT-LLM13.0580.xx+
vLLM12.9575.xx+
13.0580.xx+Experimental
0.8.0SGLang12.9575.xx+
13.0580.xx+Experimental
TensorRT-LLM13.0580.xx+
vLLM12.9575.xx+
13.0580.xx+Experimental
0.7.1SGLang12.8570.xx+
TensorRT-LLM13.0580.xx+
vLLM12.9575.xx+
0.7.0SGLang12.9575.xx+
TensorRT-LLM13.0580.xx+
vLLM12.8570.xx+

Patch versions (e.g., v0.8.1.post1, v0.7.0.post1) have the same CUDA support as their base version.

Experimental CUDA 13 images are not published for all versions. Check Release Artifacts for availability.

For detailed artifact versions and NGC links (including container images, Python wheels, Helm charts, and Rust crates), see the Release Artifacts page.

CUDA Compatibility Resources

For detailed information on CUDA driver compatibility, forward compatibility, and troubleshooting:

  • CUDA Compatibility Overview
  • Why CUDA Compatibility
  • Minor Version Compatibility
  • Forward Compatibility
  • FAQ

For extended driver compatibility beyond the minimum versions listed above, consider using cuda-compat packages on the host. See Forward Compatibility for details.

Hardware Compatibility

CPU ArchitectureStatus
x86_64Supported
ARM64Supported

Dynamo provides multi-arch container images supporting both AMD64 (x86_64) and ARM64 architectures. See Release Artifacts for available images.

GPU Compatibility

If you are using a GPU, the following GPU models and architectures are supported:

GPU ArchitectureStatus
NVIDIA Blackwell ArchitectureSupported
NVIDIA Hopper ArchitectureSupported
NVIDIA Ada Lovelace ArchitectureSupported
NVIDIA Ampere ArchitectureSupported

Platform Architecture Compatibility

Dynamo is compatible with the following platforms:

Operating SystemVersionArchitectureStatus
Ubuntu22.04x86_64Supported
Ubuntu24.04x86_64Supported
Ubuntu24.04ARM64Supported
CentOS Stream9x86_64Experimental

Wheels are built using a manylinux_2_28-compatible environment and validated on CentOS Stream 9 and Ubuntu (22.04, 24.04). Compatibility with other Linux distributions is expected but not officially verified.

KV Block Manager is supported only with Python 3.12. Python 3.12 support is currently limited to Ubuntu 24.04.

Cloud Service Provider Compatibility

AWS

Host Operating SystemVersionArchitectureStatus
Amazon Linux2023x86_64Supported

AL2023 TensorRT-LLM Limitation: There is a known issue with the TensorRT-LLM framework when running the AL2023 container locally with docker run --network host ... due to a bug in mpi4py. To avoid this issue, replace the --network host flag with more precise networking configuration by mapping only the necessary ports (e.g., 4222 for nats, 2379/2380 for etcd, 8000 for frontend).

Build Support

For version-specific artifact details, installation commands, and release history, see Release Artifacts.

Dynamo currently provides build support in the following ways:

  • Wheels: We distribute Python wheels of Dynamo and KV Block Manager:

    • ai-dynamo
    • ai-dynamo-runtime
    • kvbm as a standalone implementation.

  • Dynamo Container Images: We distribute multi-arch images (x86 & ARM64 compatible) on NGC:

    • Dynamo Frontend (New in v0.8.0)
    • SGLang Runtime
    • SGLang Runtime (CUDA 13)
    • TensorRT-LLM Runtime
    • TensorRT-LLM Runtime (EFA) (New in v1.0.0, Experimental, AMD64 only)
    • vLLM Runtime
    • vLLM Runtime (CUDA 13)
    • vLLM Runtime (EFA) (New in v1.0.0, Experimental, AMD64 only)
    • Kubernetes Operator
    • Snapshot Agent (New in v1.0.0, Preview)

  • Helm Charts: NGC hosts the helm charts supporting Kubernetes deployments of Dynamo:

    • Dynamo Platform (now includes CRDs)
    • Snapshot (New in v1.0.0, Preview)
    • Dynamo CRDs (Deprecated in v1.0.0, CRDs managed by Operator)
    • Dynamo Graph (Deprecated in v0.9.0)

  • Rust Crates:

    • dynamo-runtime
    • dynamo-llm
    • dynamo-async-openai
    • dynamo-parsers
    • dynamo-config (New in v0.8.0)
    • dynamo-memory (New in v0.8.0)
    • dynamo-tokens (New in v0.9.0)
    • dynamo-mocker (New in v1.0.0)
    • dynamo-kv-router (New in v1.0.0)

Once you’ve confirmed that your platform and architecture are compatible, you can install Dynamo by following the Local Quick Start in the README.