필터 결과
3개정렬
1:50:48EN
Y Combinator· 2026년 10월 24일Why Inference Matters 12× More Than TrainingFrançois Chaubard, Dan Fu, Jeff Morgan, Joe Fioti, Liangsheng Yin · Y CombinatorYC Paper Club walks the inference stack from an API request down to GPU kernels. Four talks from Together AI, Ollama, Luminal, and SGLang argue that serving quality, not just training FLOPs, is where most of the compute and the money now sit.
29:36ENJane Street on GPU Infrastructure, Trading and HiringDwarkesh Patel, Yaron Minsky, Daniel Pontecorvo · Dwarkesh PatelDwarkesh Patel speaks with Ron Minsky and Dan Pontecorvo about trading at different speeds, building data centers and expanding compute and teams.
47:43ENMaking GPU Training Faster: Pipelines, Fusion and Custom KernelsCorwin de Zahr · Jane StreetTwo Jane Street speakers explain how to diagnose idle GPUs, reduce memory traffic and build a parallel reduction kernel.