AMD to present MXFP8 pretraining scaling on 1K+ MI355X GPUs at PyTorchCon 2026

PyTorch · x · 2026-09-25

PyTorchCon North America 2026 preview: AMD's Liz Li and Shekhar Pandey will present scaling MXFP8 pretraining on 1K+ AMD Instinct MI355X GPUs, covering MXFP8 operator optimization in TorchAO, integration with TorchTitan for an end-to-end upstream LLM training stack, plus Triton and FlyDSL implementations and lessons from numerical validation, convergence and performance tuning. The conference runs Oct 20-21 in San Jose.

Original post →

More from Infra

Infra channel →