Gunjan Mehta

Gunjan Mehta is a senior product manager for the Deep Learning Inference Platform SW at NVIDIA. He focuses on bringing TensorRT-accelerated inference to NVIDIA RTX GeForce laptops and desktops and edge devices like embedded and DRIVE platforms. In his 10+ years of experience at NVIDIA, he has spent most of his time as a compiler engineer for the NVIDIA Deep Learning Inference Accelerator ASIC. He received his M.Sc. in computer engineering from Carnegie Mellon University in 2013, where he specialized in systems software engineering.
Avatar photo

Posts by Gunjan Mehta

Decorative image.
AI Platforms / Deployment

NVIDIA TensorRT for RTX Introduces an Optimized Inference AI Library on Windows 11

AI experiences are rapidly expanding on Windows in creativity, gaming, and productivity apps. There are various frameworks available to accelerate AI inference... 9 MIN READ
Four tiles of city scenes.
Content Creation / Rendering

NVIDIA TensorRT Unlocks FP4 Image Generation ?for NVIDIA Blackwell GeForce RTX 50 Series GPUs

The launch of the NVIDIA Blackwell platform ushered in a new era of improvements in generative AI technology. At its forefront is the newly launched GeForce RTX... 11 MIN READ
Decorative image of TensorRT workflow on a black background.
Edge Computing

Maximum Performance and Minimum Footprint for AI Apps with NVIDIA TensorRT Weight-Stripped Engines

NVIDIA TensorRT, an established inference library for data centers, has rapidly emerged as a desirable inference backend for NVIDIA GeForce RTX and NVIDIA RTX... 8 MIN READ