Skip to main content
Ctrl+K
NVIDIA Dynamo Documentation - Home

NVIDIA Dynamo Documentation

  • GitHub
NVIDIA Dynamo Documentation - Home

NVIDIA Dynamo Documentation

  • GitHub

Table of Contents

Getting Started

  • Quickstart
  • Installation
  • Support Matrix
  • Architecture
    • Overview
    • Disaggregated Serving
  • Examples

Kubernetes Deployment

  • Quickstart (K8s)
  • Dynamo Operator
  • Metrics
  • Logging
  • Multinode
  • Minikube Setup

Components

  • Backends
    • vLLM
    • SGLang
    • TensorRT-LLM
  • Router
  • Planner
    • Overview
    • Pre-Deployment Profiling
    • Load-based Planner
    • SLA-based Planner
  • KVBM
    • Overview
    • Motivation
    • KVBM Architecture
    • Understanding KVBM components
    • KVBM Further Reading
    • LMCache Integration

Developer Guide

  • Tuning Disaggregated Serving Performance
  • Writing Python Workers in Dynamo
  • Glossary
  • dynamo.nixl_...

dynamo.nixl_connect.DeviceKind(IntEnum)#

Represents the kind of device a Device object represents.

Values#

CUDA#

CUDA addressable device (GPU) memory.

HOST#

System (CPU) memory.

Related Classes#

  • Connector

  • Descriptor

  • Device

  • OperationStatus

  • RdmaMetadata

  • ReadOperation

  • WritableOperation

  • WriteOperation

On this page
  • Values
    • CUDA
    • HOST
  • Related Classes
NVIDIA NVIDIA
Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2024-2025, NVIDIA CORPORATION & AFFILIATES.