No Priors·
Stefano Ermon on why diffusion models are built for the GPU
Stefano Ermon· Co-founder & CEO of Inception; Stanford professor
Stefano Ermon, a pioneer of diffusion models and CEO of Inception, argues the next AI edge may come as much from fitting the model to the GPU as from making it smarter: diffusion generates tokens in parallel, so inference stops being a memory-bound crawl and starts using the chip the way training does.
LLMInferenceAI InfrastructureAI Company
