Technology

TensorRT

NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime that maximizes throughput and minimizes latency on NVIDIA GPUs.

TensorRT optimizes models from frameworks like PyTorch and TensorFlow for production deployment on NVIDIA hardware. It employs precision calibration (INT8 and FP16), layer fusion, and kernel auto-tuning to deliver up to 40x faster throughput than CPU-only platforms. Engineers use the ONNX workflow to deploy these engines across the NVIDIA ecosystem: from Jetson modules at the edge to H100 clusters in the data center. By maximizing CUDA core utilization and reducing memory overhead, TensorRT ensures real-time responsiveness for computer vision and generative AI applications.

https://developer.nvidia.com/tensorrt

What builders pair with TensorRT

Projects using both technologies. Select a pairing to see a project.

Built with TensorRT

CUDA 1 shared project diffprivlib 1 shared project FFmpeg 1 shared project Google Differential Privacy Library 1 shared project Groq 1 shared project GStreamer 1 shared project

12 more pairings

H 1 shared project KServe 1 shared project Multimodal Models 1 shared project NVIDIA DeepStream 1 shared project ONNX Runtime 1 shared project OpenCV 1 shared project OpenDP 1 shared project OpenVINO 1 shared project PyDP 1 shared project RNN 1 shared project RTSP 1 shared project Seldon Core 1 shared project

Pairing: CUDA

Seguridad Infantil: El Uso de Cámaras de Video e IA para el Cuidado de Niños

Bogotá · November 28, 2024

view project | view CUDA

Recent Talks & Demos

Showing 1-2 of 2

Members-Only

Sign in to see who built these projects

Sign in View FAQ

IA en Seguridad y Cuidado Infantil

RNN Transfer learning

Multimodal Groq Demo

Groq Multimodal Models