GPU-optimized AI, Machine Learning, & HPC Software

NVIDIA

The Dynamo vLLM runtime image is a containerized build of Dynamo + vLLM which serves as the base runtime environment for vLLM based inference with Dynamo's distributed inference framework.

Container

NVIDIA

Dynamo Tensorrt-LLM Runtime

The Dynamo TensorRT-LLM runtime image is a containerized build of Dynamo + TensorRT-LLM which serves as the base runtime environment for tensorrt-llm based inference with Dynamo's distributed inference framework.

Container

NVIDIA

Dynamo Platform

A comprehensive Helm chart for deploying the NVIDIA Dynamo operator and its dependencies

Helm Chart

NVIDIA

Dynamo SGLang Runtime

The Dynamo SGLang runtime image is a containerized build of Dynamo + SGLang which serves as the base runtime environment for sglang based inference with Dynamo's distributed inference framework.

Container

NVIDIA

Dynamo kubernetes-operator

kubernetes-operator is a container that runs as part of the Dynamo cloud platform. Dynamo cloud is a kubernetes platform for deploying and managing inference services. This container manages the lifecycle of Dynamo inference deployments in kubernetes.

Container

NVIDIA

Dynamo CRDs

A Helm chart that manages Custom Resource Definitions (CRDs) for the NVIDIA Dynamo ecosystem in Kubernetes

Helm Chart

NVIDIA

Dynamo Frontend

The Dynamo frontend image is a framework-less image which contains core Dynamo components along with Endpoint Picker (EPP) for Gateway API Inference Extension (GAIE).

Container

NVIDIA

Dynamo Snapshot-Agent

Dynamo Snapshot Agent enables CRIU-based checkpoint and restore for GPU inference workloads running on NVIDIA Dynamo

Container

NVIDIA

vllm-runtime-nightly

The Dynamo vLLM runtime nightly image is a containerized build of Dynamo + vLLM which serves as the base runtime environment for vLLM based inference with Dynamo's distributed inference framework published at a nightly cadence.

Container

NVIDIA

sglang-runtime-nightly

The Dynamo SGLang runtime nightly image is a containerized build of Dynamo + SGLang which serves as the base runtime environment for sglang based inference with Dynamo's distributed inference framework which is published every night.

Container

NVIDIA

tensorrtllm-runtime-nightly

The Dynamo TensorRT-LLM runtime nightly image is a containerized build of Dynamo + TensorRT-LLM which serves as the base runtime environment for tensorrt-llm based inference with Dynamo's distributed inference framework published at a nightly cadence.

Container

NVIDIA

Dynamo Planner

The Dynamo Planner image is a containerized build of Planner which serves as the runtime environment for SLA-driven autoscaling of prefill and decode workers in Dynamo's distributed inference framework.

Container

NVIDIA

snapshot

A Helm chart for deploying NVIDIA Dynamo Snapshot checkpoint/restore infrastructure on Kubernetes.

Helm Chart

NVIDIA

Dynamo Graph

A Helm chart for deploying NVIDIA Dynamo graphs on Kubernetes

Helm Chart

NVIDIA

Dynamo deployment-api

deployment-api is a container that runs as part of the Dynamo cloud platform, a k8s platform for deploying and managing inference services. It runs the Dynamo API store, a service that stores and manages service configurations, metadata and artifacts.

Container

NVIDIA

Dynamo Planner Nightly

The Dynamo Planner Nightly image is a containerized build of Planner that serves as the runtime environment for SLA-driven autoscaling of prefill and decode workers in Dynamo's distributed inference framework. It is published on a nightly cadence.

Container

NVIDIA

Dynamo kubernetes-operator-nightly

kubernetes-operator-nightly is a container that runs as part of the Dynamo cloud platform released at nightly cadence. Dynamo cloud is a kubernetes platform for deploying and managing inference services.

Container

NVIDIA

Dynamo Snapshot-Agent Nightly

Dynamo Snapshot Agent Nightly enables CRIU-based checkpoint and restore for GPU inference workloads running on NVIDIA Dynamo and publishes at nightly cadence.

Container

NVIDIA

Dynamo Frontend Nightly

The Dynamo frontend nightly image is a framework-less image which contains core Dynamo components along with Endpoint Picker (EPP) for Gateway API Inference Extension (GAIE) and is published at nightly cadence.

Container

NVIDIA

Dynamo Snapshot-Agent Dependencies

Packaged source dependencies for the `ai-dynamo/snapshot-agent` container.

Resource

Collection

NVIDIA

NVIDIA Dynamo

NVIDIA Dynamo is a high-throughput low-latency inference framework designed for serving generative AI and reasoning models in multi-node distributed environments.

1853