AI 导读
TPU🚨 正在与热门 OSS 推理优化库 Mooncake 合作，将 TPU 与 Mooncake Store 集成。与 NVL72 类似，KVCache DRAM P2P 池化最初将通过 TENT 在横向扩展网络上进行，而非使用 ICI/NVLink。🔥 Mooncake 基本上提升了生产推理的每 TCO 性能！
正文
TPU🚨 is working with the popular OSS inference optimization library Mooncake on integrating TPU with Mooncake Store. Similar to NVL72, KVCache DRAM P2P pooling will initially happen on the scale-out network via TENT instead of using ICI/NVLink. 🔥 Mooncake basically improves performance per TCO of production inference!
来源：@SemiAnalysis_ · x.com