Elias Bermudez

Elias Bermudez is a Senior System Software Engineer at NVIDIA leading the development of GenAI-Perf for the Triton Tools Team. He specializes in providing tools to profile inference performance of AI models. He cares deeply about connecting users with easy to use and powerful software, always iterating to achieve that goal. He holds a Masters of Engineering and BS from Cornell University in Electrical and Computer Engineering as well as a BS in Computer Science from Portland State University.
Avatar photo

Posts by Elias Bermudez

Decorative image of a datacenter with floating icons overlaid.
Generative AI May 06, 2025

LLM Inference Benchmarking Guide: NVIDIA GenAI-Perf and NIM

This is the second post in the LLM Benchmarking series, which shows how to use GenAI-Perf to benchmark the Meta Llama 3 model when deployed with NVIDIA NIM.?... 11 MIN READ
Generative AI Apr 02, 2025

LLM Inference Benchmarking: Fundamental Concepts

This is the first post in the large language model latency-throughput benchmarking series, which aims to instruct developers on common metrics used for LLM... 15 MIN READ
Decorative image.
Generative AI 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