Skip to main content
ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator

Search

Search thousands of GPU-optimized Containers, pretrained Models, SDKs, and Helm charts—ready to accelerate AI, digital twins, and HPC from cloud to edge.
Accelerate custom generative AI app deployment using pre-built containers with optimized AI models.

Displaying 46 results

DOCA Telemetry Service
NVIDIA
DOCA Telemetry Service (DTS) is a DOCA Service for collecting and exporting telemetry data. Both predefined and user-defined telemetry counters are available and the export is made by Prometheus, Fluent Bit, Open Telemetry and netflow.
Container
DOCA HBN
NVIDIA
Host based networking (HBN) is a DOCA Service that runs on NVIDIA's DPU. It orchestrates network connectivity of dynamically created VMs/Containers on cloud servers. HBN service is a BGP router that supports EVPN extension to enable multi-tenant cloud.
Container
cuOpt
NVIDIA
NVIDIA® cuOpt™ is an open-source, GPU-accelerated engine for decision optimization designed to tackle large-scale problems with millions of variables and constraints.
Container
Video Storage Toolkit
NVIDIA
Video Storage Toolkit (VST) is microservice for efficient management of cameras and videos
Container
vst-storage
NVIDIA
The VST Storage Service enables management of media through uploading media files deleting files, defining aging policies, on-demand retrieval for file downloads, playback functionality
Container
NVIDIA DOCA SNAP-4
NVIDIA
NVMe/virtio-blk Storage-defined Network Accelerated Processing (SNAP) Service is based on NVIDIA's DPU and enables hardware-accelerated virtualization of local storage. Resulting in enhanced storage and networking efficiency and performance.
Container
DOCA HBN
NVIDIA
Host based networking (HBN) is a DOCA Service that runs on NVIDIA's DPU. It orchestrates network connectivity of dynamically created VMs/Containers on cloud servers. HBN service is a BGP router that supports EVPN extension to enable multi-tenant cloud.
Helm Chart
AI Perception service (Jetson)
NVIDIA
DeepStream based perception service that takes in streaming video data and performs object detection and tracking
Container
BlueMan-FrontEnd
NVIDIA
The DOCA BlueMan service is a simple and user-friendly standalone web dashboard that runs completely on NVIDIA's DPU, transparent to the host. The service consolidates all the information an admin needs to know and serves as a one stop shop.
Container
DPL RT Service
NVIDIA
The DOCA Pipeline Language Runtime Service (DPL RT Service) is an NVIDIA® BlueField® service that implements the backend functionality to manage and program the DPU datapath.
Container
BlueMan-Converter
NVIDIA
The DOCA BlueMan Converter service converts DOCA BlueMan-Frontend requests from http to gRPC.
Container
DPL Development
NVIDIA
DPL Development is an NVIDIA® container image that bundles several tools for compiling, controlling and debugging DPL applications.
Container
NVIDIA DOCA SNAP Virtio-fs
NVIDIA
NVIDIA® BlueField® DOCA SNAP Virtio-fs technology enables hardware-accelerated virtualization of local file system.
Container
AI Analytics
NVIDIA
Generate time-series insights for the physical spaces based on perception metadata.
Container
AI Analytics Web API
NVIDIA
Container for AI Analytics API service
Container
VLM Inference Service (Jetson)
NVIDIA
AI Inference Service for using VLM (visual language model) on streaming video for greater contextual understanding and natural language interaction
Container
VLM Summarization (Jetson)
NVIDIA
Provides natural language interfaces for performing video summarization
Container
Zero Shot Inference Service (Jetson)
NVIDIA
AI Inference service to perform zero-shot (open vocabulary) object detection of any objects on streaming video data
Container
Kumo Relational Foundation Model (NIM)
NVIDIA
Structured data relational foundation model
Container
OVN Domain Service
NVIDIA
The OVN Domain Service is a gRPC server simplifying OVN consumption, an open-source network virtualization platform. It provides a simplified interface for building and configuring networking components enabling domain isolation.
Container
DOCA Firefly
NVIDIA
A Helm chart for deploying DOCA Firefly service that provides time synchronization services leveraging the hardware acceleration of the NVIDIA DPUs.
Helm Chart
cuOpt
NVIDIA
A Helm chart for deploying the Nvidia cuOpt Server
Helm Chart
Jetson Platform Services Reference Workflow & Resources
NVIDIA
Jetson Platform Services Reference Workflow & Resources
Resource
Kumo Tabular NIM
NVIDIA
Model for prediction on tabular data
Container
1-24 of 46 items

Modal Content

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.

Manage Settings