AI云服务普遍依赖NVIDIA芯片
精选理由
General Compute用4亿美元采购Cerebras，试图挑战NVIDIA在AI云服务领域的垄断地位。
几乎所有AI云服务都运行在NVIDIA芯片上。General Compute公司计划改变这一现状，已投入4亿美元债务资金采购Cerebras系统。Cerebras芯片将部署在NVIDIA GPU旁边，处理请求时两者协同工作。Cerebras的优势在于权重存储在片上SRAM中，解码过程不会因内存带宽而停滞。
原文 · rohanpaul_ai
Pretty much every AI cloud runs on NVIDIA.
General Compute wants to be the one that runs everything else: Cerebras, SambaNova, Etched.
Their first big move is a large Cerebras purchase, funded by $400M in debt. Those machines will sit next to NVIDIA GPUs, and each request gets split between them.
GPUs read the prompt. Cerebras writes the answer, and it's fast because the weights live in on-chip SRAM, so decode doesn't stall on memory bandwidth.
