Rohan Paul· @rohanpaul_ai · X·· 3 小时前AI 评分40
AI 导读
几乎所有 AI 云都跑在 NVIDIA 上。 General Compute 想成为运行其他一切的那一个：Cerebras、SambaNova、Etched。 他们的第一个大动作是大规模采购 Cerebras，由 4 亿美元债务融资。这些机器将与 NVIDIA GPU 并排放置，每个请求在两者之间拆分。 GPU 读取提示词。Cerebras 写出答案，速度很快，因为权重存在片上 SRAM 中，所以解码不会因内存带宽而停滞。
正文
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.
🚨 BREAKING: Super excited to announce we're deploying the world's fastest inference with @Cerebras. Talk to any developer and they're excited to build with 20x faster AI... the problem is there's almost no compute available. We're here to solve that. Using GPUs for prefill - it's now more affordable than ever too. Thank you to the whole Cerebras team and excited to grow this partnership. First tokens live Q127 🚀在 X 查看被引用的帖子
来源：Rohan Paul · x.com