gpus
9 talks
Can LLMs Write Fast Multi-GPU Kernels?
Infra behind Krea 2: How to train and serve at scale
The Next Medium: Why Real-Time Interactive Video Changes Everything
Gradient-Free Continual Learning
The Desktop Frontier
You Might Not Need 50 Diffusion Steps
GPU Cloud Deployment Without Leaving Your IDE
Road to 5 Million Tokens: Breaking Barriers in Long Context Training
Under 5 minutes to a deployed LLM endpoint