Rachel Oberman

Rachel Oberman is an AI Solutions Architect at NVIDIA who specializes in optimizing and productizing AI applications for the consumer Internet industry. She has over five years of experience working in end-to-end AI pipelines including analytics, training, and inference workloads and a background in geospatial analysis. She holds a Master's degree in Computer Science from Columbia University, and a Bachelor's degree in Computer Science and Data Science from the College of William & Mary.
Avatar photo

Posts by Rachel Oberman

Decorative image.
Generative AI Jul 01, 2025

Per-Tensor and Per-Block Scaling Strategies for Effective FP8 Training

In this blog post, we’ll break down the main FP8 scaling strategies—per-tensor scaling, delayed and current scaling, and per-block scaling (including the... 10 MIN READ