NVIDIA Jetson AGX Xavier Delivers 32 TeraOps for New Era of AI in Robotics

Artificial Intelligence, Autonomous Vehicles, Robotics, autnomous vehicles, Featured, Jetpack, Jetson AGX Xavier, machine learning and AI, NVIDIA AGX, TensorRT

Nadeem Mohammad, posted Dec 12 2018

The world’s ultimate embedded solution for AI developers, Jetson AGX Xavier, is now shipping as standalone production modules from NVIDIA.

Read more

NVIDIA TensorRT Inference Server Now Open Source

Artificial Intelligence, Development Tools & Libraries, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Nov 20 2018

In September 2018, NVIDIA introduced NVIDIA TensorRT Inference Server, a production-ready solution for data center inference deployments.

Read more

How to Speed Up Deep Learning Inference Using TensorRT

Artificial Intelligence, C++, Deep Learning, Development Tools and Libraries, Featured, Inference, machine learning and AI, ONNX, ResNet50, TensorRT

Nadeem Mohammad, posted Nov 08 2018

Welcome to this introduction to TensorRT, our platform for deep learning inference. You will learn how to deploy a deep learning application onto a GPU, increasing throughput and reducing latency during inference.

Read more

Using MATLAB and TensorRT on NVIDIA GPUs

Artificial Intelligence, Computer Vision & Machine Vision, CUDA, Development Tools & Libraries, Machine Learning & Artificial Intelligence, MATLAB, TensorRT

Nadeem Mohammad, posted Oct 09 2018

MathWorks recently released MATLAB R2018b which integrates with NVIDIA TensorRT through GPU Coder. With this integration, scientists and engineers can achieve faster inference performance on GPUs from within MATLAB.

Read more

NVIDIA TensorRT Inference Server Available Now

Accelerated Computing, Artificial Intelligence, Computer Vision & Machine Vision, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Sep 25 2018

The NVIDIA TensorRT inference server GA version is now available for download in a container from the NVIDIA GPU Cloud container registry.

Read more

TensorRT 5 RC Now Available

Artificial Intelligence, Features, Computer Vision & Machine Vision, CUDA, cuDNN, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Sep 20 2018

AT GTC Japan, NVIDIA announced the latest version of the TensorRT’s high-performance deep learning inference optimizer and runtime.

Read more

NVIDIA DGX-2 AI Supercomputer and New Tesla T4 Set Image Recognition Records for Training and Inference

Artificial Intelligence, Features, Cloud, Machine Learning & Artificial Intelligence, TensorRT, Tesla

Nadeem Mohammad, posted Sep 12 2018

Earlier this year, we talked about performance breakthroughs enabled by two new technologies we developed. Related to data augmentation and tensor parameter interleaving, these technologies enabled a single Tesla V100 GPU to do a ResNet-50 trainin

Read more

Video Tutorial: Introduction to Recurrent Neural Networks in TensorRT

Artificial Intelligence, Features, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Aug 20 2018

NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime that delivers low latency and high-throughput.

Read more

Video Tutorial: Accelerating Inference Performance of Recommendation Systems with TensorRT

Artificial Intelligence, Features, Machine Learning & Artificial Intelligence, TensorRT

Nadeem Mohammad, posted Aug 03 2018

NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications.

Read more