General Compute 与 Positron AI 达成多年合作,提供 Atlas 推理系统
Positron 的 Atlas 推理芯片又多了一个云渠道,GPU 管输入、专用芯片管输出,想省推理成本的话这个组合值得看看。
General Compute 与 Positron AI 签署多年合作协议,向云客户出租 Positron 的 Atlas 推理系统。Atlas 已在 Oracle Cloud Infrastructure 上可用,General Compute 还承诺集成下一代 Titan 系统。其架构中 GPU 负责处理每个请求的输入,Positron 芯片利用快速内存访问优势更高效地生成输出 token。客户无需购买硬件即可租用专用 AI 芯片的算力。
General Compute has signed a multi-year partnership with @positron_ai to offer Positron's Atlas inference systems to its cloud customers.
General Compute buys and runs specialized AI chips alongside GPUs, allowing AI companies to rent processing power and use Positron hardware without buying it.
> GPUs handle the input process for each request, so Positron chips generate the output more efficiently.
> Positron’s chips are built with a focus on fast memory access since it is one of the main bottlenecks for token generation.
> Atlas is already available inside Oracle Cloud Infrastructure, with General Compute also committing to integrate Positron's next-generation Titan systems.