David Yastremsky

David Yastremsky is a senior system software engineer at NVIDIA, specializing in profiling AI model inference on Triton Tools. With extensive experience in developing Triton Inference Server and the Clara Platform for Healthcare AI, David is committed to democratizing AI and maximizing its potential for social good. He holds a master's degree in computer science from the University of Pennsylvania.
Avatar photo

Posts by David Yastremsky

Decorative image.
Generative AI / LLMs Aug 01, 2024

Measuring Generative AI Model Performance Using NVIDIA GenAI-Perf and an OpenAI-Compatible API

NVIDIA offers tools like Perf Analyzer and Model Analyzer to assist machine learning engineers with measuring and balancing the trade-off between latency and... 6 MIN READ
Data Science Aug 27, 2020

Maximizing Deep Learning Inference Performance with NVIDIA Model Analyzer

You’ve built your deep learning inference models and deployed them to NVIDIA Triton Inference Server to maximize model performance. How can you speed up the... 8 MIN READ