PyTorch dev ships interactive roofline explainer with NVIDIA GPU and HBM/network analysis

ezyang · x · 2026-09-20

PyTorch core dev ezyang had Astra turn the roofline chapter of 'How to Scale Your Model' into an explorable explanation: switchable between TPU and NVIDIA GPUs, with split HBM and network bandwidth analysis. Readers can tweak batch size, hidden dims, precision (BF16/FP8/INT8), compute/bandwidth multipliers and overlap, and see live roofline bounds on computation time. The original essay is from the Google DeepMind Scaling Book (Feb 2025); adaptation sections were written with OpenAI Codex.

Original post →

More from Infra

Infra channel →