Tanay Varshney

Tanay Varshney is a senior developer advocate engineer at NVIDIA responsible for a wide range of DL software products. He has a master's degree in computer science from New York University focused on the cross section of computer vision, data visualization, and urban analytics.
Avatar photo

Posts by Tanay Varshney

Decorative image of a user at a computer and the screen is showing input from an LLM in the background.
Generative AI / LLMs Nov 30, 2023

Building Your First LLM Agent Application

When building a large language model (LLM) agent application, there are four key components you need: an agent core, a memory module, agent tools, and a... 10 MIN READ
Decorative image of a user at a computer and the screen is showing input from an LLM in the background.
Generative AI / LLMs Nov 30, 2023

Introduction to LLM Agents

Consider a large language model (LLM) application that is designed to help financial analysts answer questions about the performance of a company. With a... 10 MIN READ
Generative AI / LLMs Apr 26, 2023

An Introduction to Large Language Models: Prompt Engineering and P-Tuning

ChatGPT has made quite an impression. Users are excited to use the AI chatbot to ask questions, write poems, imbue a persona for interaction, act as a personal... 10 MIN READ
NeMo Guardrails illustration.
Generative AI / LLMs Apr 25, 2023

NVIDIA Enables Trustworthy, Safe, and Secure Large Language Model Conversational Systems

Large language models (LLMs) are incredibly powerful and capable of answering complex questions, performing feats of creative writing, developing, debugging... 7 MIN READ
Data Science Jul 20, 2022

Optimizing and Serving Models with NVIDIA TensorRT and NVIDIA Triton

Imagine that you have trained your model with PyTorch, TensorFlow, or the framework of your choice, are satisfied with its accuracy, and are considering... 11 MIN READ
Data Center / Cloud May 11, 2022

Accelerating AI Inference Workloads with NVIDIA A30 GPU

NVIDIA A30 GPU is built on the latest NVIDIA Ampere Architecture to accelerate diverse workloads like AI inference at scale, enterprise training, and HPC... 6 MIN READ