AI 导读
在每美元总 token 数（TCO）上，AMD MI355x 的新提交在 AgentX 上于较低交互性区间击败了 B300。两种高吞吐配置均采用分离式架构。感谢 vLLM、AMD 和 LMCache 的工程师们。https://t.co/Sc35IXkXY8
正文
On total tokens per $ TCO, a new AMD MI355x submission beats B300 at lower interactivity ranges on AgentX. Both high throughput configs use disaggregated setups. Shoutout to vLLM, AMD, and LMCache engineers. https://t.co/Sc35IXkXY8
来源：@SemiAnalysis_ · x.com