Sergio Perez

Sergio Perez is a solution architect at NVIDIA who specializes in the training and inference of LLMs. Sergio works alongside AI developers in public supercomputer centers and sectors such as energy, automotive, finance, telecommunications, and internet services. He has contributed to production applications of LLMs covering RAG systems, optimization of inference servers, pretraining of LLMs from scratch, custom evaluation of LLMs, or quantization using FP8 formats. Sergio holds a Ph.D. in computational fluid dynamics from Imperial College London.
Avatar photo

Posts by Sergio Perez

Decorative image.
Agentic AI / Generative AI Jun 18, 2025

LLM Inference Benchmarking: How Much Does Your LLM Inference Cost?

Learn how to calculate LLM inference costs using NVIDIA GenAI-Perf benchmarking tools and TCO formulas. This guide covers performance metrics (TTFT,... 11 MIN READ
A decorative image.
Agentic AI / Generative AI Jun 04, 2025

Floating-Point 8: An Introduction to Efficient, Lower-Precision AI Training

With the growth of large language models (LLMs), deep learning is advancing both model architecture design and computational efficiency. Mixed precision... 11 MIN READ
Stack diagram for LLM Megatron Core.
Data Center / Cloud Jan 16, 2025

Continued Pretraining of State-of-the-Art LLMs for Sovereign AI and Regulated Industries with Domyn and NVIDIA DGX Cloud

In recent years, large language models (LLMs) have achieved extraordinary progress in areas such as reasoning, code generation, machine translation, and... 17 MIN READ