English(EN) Google split its eighth-generation Tensor Processing Unit between training and inference at Google Cloud Next. TPU 8t superpods scale to 9,600 chips, 2 PB of sh

Google发布新款TPU 8t，用于AI训练和推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-09 13:36

Google发布了其第八代张量处理单元（TPU），旨在优化AI训练和推理任务。新款TPU 8t超级集群将包含多达9,600个芯片，提供121 ExaFlops的计算能力和2 PB的内存。Google的目标是通过利用片上SRAM和高带宽内存，使TPU 8i的每美元性能提升80%，预计两个版本将于今年晚些时候上市。 AI

影响 AI加速器硬件的这一进步可能会显著提高训练和部署大型AI模型的效率和成本效益。

排序理由前沿实验室模型发布，带有系统卡[lever_c 从 frontier_release 降级：ic=1 ai=0.7]

在 Mastodon — mastodon.social 阅读 →

基础设施

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Significant; 前沿实验室模型发布，带有系统卡[lever_c 从 frontier_release 降级：ic=1 ai=0.7]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — mastodon.social TIER_1 English(EN) · [email protected] · 2026-11-09 13:36

谷歌在Google Cloud Next上将其第八代Tensor Processing Unit拆分为训练和推理。TPU 8t超级集群扩展到9,600个芯片，2 PB的存储

Google split its eighth-generation Tensor Processing Unit between training and inference at Google Cloud Next. TPU 8t superpods scale to 9,600 chips, 2 PB of shared high-bandwidth memory, and 121 ExaFlops. TPU 8i holds a model's active working set in 384 MB of on-chip SRAM alongs…

本文如何被排名

报道来源 [1]

谷歌在Google Cloud Next上将其第八代Tensor Processing Unit拆分为训练和推理。TPU 8t超级集群扩展到9,600个芯片，2 PB的存储

相关实体

相关话题