Published at 10/19/2026, 12:06:03 AM · 83 views
📰 SemiAnalysis Discloses Google & Inferact TPUv7 Submission: TorchTPU vLLM Megakernels Drive 2.8T Kimi K3, Surpassing GB200 NVL72 and B300 in High-Interactivity…
SemiAnalysis revealed the first Google TPUv7 benchmark submission for the 2.8T Kimi K3 MoE model, led end-to-end by Inferact (the creators of vLLM) and Google using the TorchTPU vLLM stack.
💬 What's your take? Join the discussion in the comments.
Read the original Chinese version
📰 SemiAnalysis 披露 Google 与 Inferact 首份 TPUv7 评测：TorchTPU vLLM 大核驱动 2.8T Kimi K3，高交互吞吐力压 GB200 NVL72 与 B300
半导体分析机构 SemiAnalysis 发布最新评测：Inferact（vLLM 核心团队）联合 Google 正式提交了首份基于 Google TPUv7 的 Kimi K3 2.8T 巨型 MoE 模型推理基准。
💬 你怎么看？欢迎在评论区讨论。
#SemiAnalysis #TPUv7 #vLLM
0 Comments