跳到正文
Hacker News:AI 熱帖·· 13 天前AI 評分51

Google 公佈面向智能體時代的新款 TPU 8tx 和 8i Max

Our newest TPUs: 8tx and 8i Max, built for the agentic era

AI 導讀

Google 公佈新款 TPU 8tx 和 8i Max,定位為面向智能體時代的加速器。貼文引述的 Agent Compute Engine 軟件會自動暫停閒置的智能體工作階段,並在毫秒內把工作記憶體移出晶片,以降低營運基礎設施成本。

正文

Image 1Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Our newest TPUs: 8tx and 8i Max, built for the agentic era (blog.google) 25 points by meetpateltech10 hours ago | hide | past | favorite | 4 comments help Image 2pierreb-aiva9 hours ago | next[–] > Because AI agents are stateful, they frequently pause for seconds or hours while waiting on a database lookup, an external software tool, or human feedback. To make our accelerators more power-efficient during those pauses, our new Agent Compute Engine software automatically suspends idle agent sessions and shifts working memory off the chip in milliseconds, cutting operational infrastructure costs Nice. I wonder how they manage to move kv cache from working memory to disk so quickly to enable speed ups when pauses are a few seconds at most reply Image 3jononor5 hours ago | parent | next[–] Off chip does not have to mean to disk? I would assume a staged approach. First offload to CPU RAM, and then to disk (if not used within a few seconds), and then to network storage (so it can maybe be resumed by other machines). And some request routing that makes use of cache affinity based on session/user. reply Image 4gniv10 hours ago | prev | next[–] Seems like a big deal, but there's nothing about availability. They might say more during the broadcast later today. reply Image 5xnx9 hours ago | prev[–] More bad news for Nvidia today. reply Image 6 Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:

來源:Hacker News:AI 熱帖 · news.ycombinator.com