ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
SearchSearch thousands of GPU-optimized Containers, pretrained Models, SDKs, and Helm charts—ready to accelerate AI, digital twins, and HPC from cloud to edge.
NVIDIA Enterprise
NVIDIA Enterprise
11
9
3
2
1
1
NVIDIA NIM
NVIDIA NIM
1
NIM Container GPUs
NIM Container GPUs
Use Case
Use Case
1
1
NVIDIA Platform
NVIDIA Platform
11
Industry
Industry
1
Solution
Solution
7
5
5
4
1
Publisher
Publisher
11
Policy
Policy
2
Displaying 15 results
NVIDIA
NVIDIA
Triton Inference Server
Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.
Container
NVIDIA AI Enterprise
NVIDIA
NVIDIA
Triton Inference Server PB October 2024 (PB 24h2)
Triton Inference Server Production Branch October 2024 (PB 24h2) offers a 9-month lifecycle for API stability, with monthly patches for high and critical software vulnerabilities.
Container
NVIDIA AI Enterprise
NVIDIA
NVIDIA
Triton Inference Server PB March 2025 (PB 25h1)
Triton Inference Server PB May 2025 (PB 25h1) offers a 9-month lifecycle for API stability, with monthly patches for high and critical software vulnerabilities.
Container
NVIDIA AI Enterprise
NVIDIA
NVIDIA
Triton Inference Server PB October 2025 (PB 25h2)
Triton Inference Server PB October 2025 (PB 25h2) offers a 9-month lifecycle for API stability, with monthly patches for high and critical software vulnerabilities.
Container
NVIDIA AI Enterprise
NVIDIA
NVIDIA
Triton Inference Server Long-Term Support Branch 2 (LTSB 2)
Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.
Container
NVIDIA AI Enterprise IGX
NVIDIA
NVIDIA
Tritonserver LTSB2 IGX
Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.Please add description
Container
NVIDIA AI Enterprise
NVIDIA
NVIDIA
Triton Inference Server Production Branch 6
Triton Inference Server Production Branch 6 offers a 9-month lifecycle for API stability, with monthly patches for high and critical software vulnerabilities.
Container
NVIDIA
NVIDIA
triton-sdk-2.52.0-rhel8-x86-compat-beta.zip
RHEL Triton x86 SDK Beta asset
Resource
NVIDIA
NVIDIA
triton-sdk-2.52.0-rhel8-aarch64-compat-beta.zip
RHEL Triton aarch64 SDK Beta asset
Resource
NVIDIA
NVIDIA
tritonserver2.52.0-rhel8-aarch64-compat-beta.zip
RHEL Triton aarch64 Beta asset
Resource
NVIDIA
NVIDIA
tritonserver2.52.0-rhel8-x86-compat-beta.zip
RHEL Triton x86 Beta asset
Resource
Collection
NVIDIA AI Enterprise
NVIDIA
NVIDIA
Long-Term Support Branch 2 (LTSB 2)
Access the Long-Term Support Branches (LTSB) of AI frameworks and SDKs. Supported for 36-months, with quarterly patches for high and critical software vulnerabilities.
51
Collection
NVIDIA AI Enterprise
—
Long-Term Support Branch 2 (LTSB 2) IGX
Access the Long-Term Support Branches (LTSB) of base platform software, AI frameworks and SDKs on NVIDIA IGX platform. Supported for 10-years, with quarterly patches for high and critical software vulnerabilities.
52
Collection
NVIDIA NeMo Microservices
NVIDIA
NVIDIA
Production Branch - May 2025 (PB 25h1)
Access the production branches of AI frameworks and SDKs. Supported for 9 months with monthly security patches.
111
Collection
NVIDIA AI Enterprise
NVIDIA
NVIDIA
Production Branch - October 2025 (PB 25h2)
Access the production branch images of AI frameworks and SDKs. Supported for 9 months with monthly security patches.
1411