FlashAttention-3
Hardware-aware algorithm for fast attention computation
Episodes
-
#1081: The K-V Cache: Solving AI’s Invisible Memory TaxWhy does your AI get slower as you chat? Discover the K-V cache, the invisible bottleneck of generative AI, and how we're fixing it in 2026. -
#267: Decoding the Transformer: From Attention to InferenceHerman and Corn dive into the mechanics of transformer inference, exploring how models turn massive matrices into meaningful conversation.