Kürzlich aktualisierte Kanäle

Wählen, um nur diesen Kanal zu sehenAlle Kanäle →
20VC with Harry Stebbingsgestern +173JSJane Streetgestern +119AI Engineergestern +1硅谷101vorgesternMBMatthew Bermanvor 3 Tagen +111PragerUvor 3 TagenY Combinatorvor 3 Tagena16zvor 4 Tagen +1SemiAnalysisvor 4 TagenGOTO Conferencesvor 4 Tagen

Ergebnisse

1 Artikel
Sortieren
ThemaKV caching & prefix reuseLängeÜber 30 Min.
32 Folien1:50:48EN
Y Combinator· 24. Okt. 2026Why 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.InferenceGPU programming & kernelsKV caching & prefix reuse+2