GPU-optimized AI, Machine Learning, & HPC Software

NVIDIA

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.

Container

NVIDIA

NVOF

NVOF is a deep learning based optical flow estimation and stereo matching solution.

Model

NVIDIA

TensorRT LLM Develop

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.

Container

NVIDIA AI Enterprise

NVIDIA

TensorRT PB October 2025 (PB25h2)

TensorRT Production Branch October 2025 (PB 25h2) offers a 9-month lifecycle for API stability, with monthly patches for high and critical software vulnerabilities. This release includes Government Ready images for regulated environments.

Container

NVIDIA AI Enterprise

Nvidia

TensorRT May 2025 (PB25h1)

TensorRT Production Branch May 2025 (PB 25h1) offers a 9-month lifecycle for API stability, with monthly patches for high and critical software vulnerabilities. This release is a branch of TensorRT 25.03.

Container

NVIDIA Developer Program

NVIDIA

relighting

AI4M Relighting is an AI-powered video relighting that dynamically re-illuminates a person with virtual studio lighting using HDR environment maps. Supports adjustable lighting direction, intensity, specular highlights, and background compositing.

Container

NVIDIA AI Enterprise IGX

NVIDIA

TensorRT LTSB2 IGX

NVIDIA TensorRT is a C++ library that facilitates high-performance inference on NVIDIA graphics processing units (GPUs). TensorRT takes a trained network and produces a highly optimized runtime engine that performs inference for that network.

Container

NVIDIA

Nvidia VSS CV Event Detector

Nvidia Sample CV Event Detector Microservice for detecting events for VSS Event Reviewer workflow.

Container

NVIDIA

RT-DETR 2D Warehouse

RT-DETR object detection model for 2D warehouse applications

Model

NVIDIA

PyNvVideoCodec

PyNvVideoCodec is NVIDIA’s Python based video codec library for hardware accelerated video encode and decode on NVIDIA GPUs.

Resource

NVIDIA AI Enterprise

NVIDIA

TensorRT Production Branch 6

TensorRT Production Branch 6 offers a 9-month lifecycle for API stability, with monthly patches for high and critical software vulnerabilities. This release includes Government Ready images for regulated environments.

Container

NVIDIA

SyntheticaDETR

SytheticaDETR is a real-time object detection model based on a transformer architecture trained entirely in simulation and works on real images zero-shot.

Model

NVIDIA

PeopleSemSeg AMR

People semantic segmentation network, finetuned on robotics AMR dataset, optimized for Issac Perceptor & Nvblox.

Model

NVIDIA

Phi-2 (TensorRT LLM)

Phi-2 is a 2.7 billion parameter language model developed by Microsoft Research. The phi-2 model is best suited for prompts using the Question-Answer (QA) format, the chat format, and the code format.

Model

NVIDIA

PeopleNet AMR

People bounding box detection network, finetuned on robotics AMR dataset, optimized for multi-camera RealSense setup. Used in nvblox multi-camera optimization.

Model

NVIDIA

Llama 2 7B Chat (TensorRT LLM)

Llama 2 is a large language AI model comprising a collection of models capable of generating text and code in response to prompts.

Model

NVIDIA

Mistral 7B Instruct (TensorRT LLM)

Mistral-7B-Instruct is a language model that can follow instructions, complete requests, and generate creative text formats.

Model

NVIDIA

Gemma 2B Instruct (TensorRT LLM)

Gemma-2B is a 2.5B parameter model from Gemma family of models from Google. It has been instruction-tuned so it can respond to prompts in a conversational manner.

Model

NVIDIA

NVSaliENC

NVSaliENC uses deep learning-based saliency maps to optimize perceptual video quality in real time, prioritizing visually important regions for efficient, bandwidth-saving compression with NVENC integration.

Model

Collection

NVIDIA

Deep Learning Frameworks

This collection contains performance-optimized Deep Learning frameworks.

9

Collection

NVIDIA AI Enterprise

NVIDIA

English Parakeet 0.6b-v2 TDT collection

A collection of easy to use, highly optimized Deep Learning Models for Speech Recognition. The Parakeet collection provides Data Scientists and Software Engineers with recipes to train, fine-tune, and deploy state-of-the-art ASR models.

13

Collection

NVIDIA AI Enterprise

NVIDIA

Mandarin-English Parakeet 0.6b CTC collection

A collection of easy to use, highly optimized Deep Learning Models for Speech Recognition. The Parakeet collection provides Data Scientists and Software Engineers with recipes to train, fine-tune, and deploy state-of-the-art ASR models.

13

Collection

NVIDIA AI Enterprise

NVIDIA

Spanish Parakeet 0.6b CTC collection

A collection of easy to use, highly optimized Deep Learning Models for Speech Recognition. The Parakeet collection provides Data Scientists and Software Engineers with recipes to train, fine-tune, and deploy state-of-the-art ASR models.

13

Collection

NVIDIA AI Enterprise

NVIDIA

Taiwanese Mandarin Parakeet 0.6b CTC collection

A collection of easy to use, highly optimized Deep Learning Models for Speech Recognition. The Parakeet collection provides Data Scientists and Software Engineers with recipes to train, fine-tune, and deploy state-of-the-art ASR models.

13