Luminal runs large-scale FLUX.2 diffusion on AMD MI300X to cut cost per image

ycombinator · x · 2026-09-19

Luminal AI announces it runs large-scale FLUX.2 diffusion workloads on AMD MI300X through the Luminal compiler. Engineer Reis details how the team drives down cost per image by leveraging cheaper flops than NVIDIA hardware, demonstrating viable non-NVIDIA inference for image generation.

Original post →

More from Infra

Infra channel →