Francesco Di Natale

Francesco Di Natale is a senior performance engineer at NVIDIA where his primary focus is benchmarking methodology, workflow automation, and tooling. His technical interests include software workflow automation, software engineering, and reproducible benchmarking/simulation. Prior to joining NVIDIA, he was a computer scientist at Lawrence Livermore National Laboratory, automating large HPC molecular dynamics ensembles on Sierra and Summit. Francesco holds dual B.S degrees in computer science and computer engineering from the University of South Florida, and an M.S. in computer science from the University of Colorado at Boulder.
Avatar photo

Posts by Francesco Di Natale

Generative AI

LLM Inference Benchmarking: Performance Tuning with TensorRT-LLM

This is the third post in the large language model latency-throughput benchmarking series, which aims to instruct developers on how to benchmark LLM inference... 11 MIN READ