Jay Rodge

Jay Rodge is a product marketing manager for deep learning and inference products at NVIDIA driving launches and product marketing initiatives. Jay received his master’s degree in computer science from Illinois Tech, Chicago with a focus on computer vision and NLP. Before NVIDIA, Jay was an AI research intern at BMW Group solving problems using computer vision for BMW’s largest manufacturing plant.

Posts by Jay Rodge

Diagram of Torch-TensorRT and TensorFlow-TensorRT.
News 1 Dec 02, 2021

NVIDIA Announces TensorRT 8.2 and Integrations with PyTorch and TensorFlow

Learn about TensorRT 8.2 and the new TensorRT framework integrations, which accelerate inference in PyTorch and TensorFlow with just one line of code. 2 MIN READ
Technical Walkthrough 0 Dec 02, 2021

Optimizing T5 and GPT-2 for Real-Time Inference with NVIDIA TensorRT

TensorRT 8.2 optimizes HuggingFace T5 and GPT-2 models. You can build real-time translation, summarization, and other online NLP apps. 9 MIN READ
News 1 Nov 09, 2021

ICYMI: New AI Tools and Technologies Announced at NVIDIA GTC Keynote

New AI software tools include Riva Customer Voice, TensorRT, Triton Inference Server, Merlin, NeMo Megatron, and DeepStream. 5 MIN READ
News 2 Oct 05, 2021

NVIDIA GTC: Can’t-Miss Sessions in AI and Deep Learning this November

Register now for AI and deep learning GTC sessions focused on topics such as training, inference, frameworks, and tools. 4 MIN READ
News 0 Jul 20, 2021

NVIDIA Announces TensorRT 8 Slashing BERT-Large Inference Down to 1 Millisecond

NVIDIA announced TensorRT 8.0 which brings BERT-Large inference latency down to 1.2 ms with new optimizations. 3 MIN READ
Technical Walkthrough 0 Jul 20, 2021

Achieving FP32 Accuracy for INT8 Inference Using Quantization Aware Training with NVIDIA TensorRT

○ TensorRT is an SDK for high-performance deep learning inference and with TensorRT 8.0, you can import models trained using Quantization Aware Training (QAT) to run inference in INT8 precision with... 17 MIN READ