Purnendu Mukherjee

Purnendu Mukherjee is a senior deep learning software engineer, working in the AI Applications group at NVIDIA. His primary focus is to bring state-of-the-art, deep learning-based, speech and natural language processing models into production as part of developing the Riva platform. Prior to joining NVIDIA, Purnendu graduated from the University of Florida with a master's degree in computer science specializing in deep learning-based natural language processing.

Posts by Purnendu Mukherjee

Technical Walkthrough 0

Building and Deploying Conversational AI Models Using NVIDIA TAO Toolkit

Read up on three products for building conversational AI: NVIIDA TAO Toolkit, NVIDIA Riva, and NVIDIA NGC collections. 25 MIN READ
Technical Walkthrough 0

Real-Time Natural Language Processing with BERT Using NVIDIA TensorRT (Updated)

Today, NVIDIA is releasing TensorRT 8.0, which introduces many transformer optimizations. With this post update, we present the latest TensorRT optimized BERT sample and its inference latency benchmark on A30 GPUs. Using the optimized sample, you can execute different batch sizes for BERT-base or BERT-large within the 10 ms latency budget for conversational AI applications. 18 MIN READ
Technical Walkthrough 0

Real-Time Natural Language Understanding with BERT Using TensorRT

Large scale language models (LSLMs) such as BERT, GPT-2, and XL-Net have brought about exciting leaps in state-of-the-art accuracy for many natural language… 21 MIN READ
Technical Walkthrough 0

How to Speed Up Deep Learning Inference Using TensorRT

Introduction to accelerated creating inference engines using TensorRT and C++ with code samples and tutorial links 22 MIN READ