筛选结果
2 篇排序
17:42EN → 简体中文
AI Engineer· 2026年10月21日更快的模型，真的更快吗？要看任务做完没有，而不是 token 有多快Morgan Suo · MiniMaxMiniMax 的 Morgan Suo 逐一拆解 M3.1 Flash 内部的工程改动，追问用户真正关心的问题：分析师要的那份活，是不是真的做得更快、更便宜、也更对了？
59:06EN
Unsupervised Learning: With Jacob Effron· 2025年9月10日播客Inference Costs Fell 100x. Tri Dao Says There's Another 10x — and NVIDIA's 90% Won't Hold主持 Jacob EffronThe FlashAttention author and Together AI chief scientist on why hardware portability is a myth, how Claude Code made him 1.5x faster, and why workloads will split the chip market.