谷歌发布第八代AI芯片TPU 8tx与TPU 8i Max

1. 05:37
   ServeTheHomeSelected

   Google Unveils TPU 8tx and TPU 8i Max: Focused on Confidential Computing and Doubled Memory Bandwidth

   Google is expanding its eighth-generation TPU lineup with two new hardware systems: TPU 8tx for confidential computing and TPU 8i Max designed specifically for long-context inference. TPU 8tx uses the same silicon as the TPU 8t training chip paired with a custom 5th Gen AMD EPYC Turin host to protect data in use within a hardware-isolated environment, while adopting a Boardfly topology to reduce multi-step agentic inference latency.

2. 02:50
   Data Center KnowledgeSelected

   Google Introduces Enterprise AI Chips TPU 8tx and TPU 8i Max

   Google Cloud has launched two custom chips, the TPU 8tx and TPU 8i Max, targeting sensitive enterprise workload protection and long-context agentic inference scenarios, respectively.

3. 02:06
   The Next PlatformSelected

   Google Tweaks TPU Architecture to Launch TPU 8tx and TPU 8i Max Accelerator Variants

   Google has introduced two hardware variants, TPU 8tx and TPU 8i Max, targeted at AI inference and agentic workloads, alongside TPU Sync, a tiered memory management software.

1. 21:04
   Data Center Dynamics

   Google 扩展第八代 TPU 产品线，推出 TPU 8tx 与 TPU 8i Max

   Google 扩展了其第八代 TPU 产品线，推出 TPU 8tx 与 TPU 8i Max 两款全新 TPU 系统。其中 TPU 8tx 专为机密计算设计，TPU 8i Max 则旨在支持上下文扩展。

2. 21:00
   Google InfrastructureSelected

   Google Releases TPU 8tx and TPU 8i Max Compute Systems

   Google announced an expansion of its eighth-generation TPU portfolio, officially launching TPU 8tx for confidential inference and TPU 8i Max for ultra-long context windows. TPU 8tx features hardware-level confidential computing and Google's low-latency Boardfly interconnect, enabling secure fine-tuning and inference on sensitive data within a single system. TPU 8i Max packages two TPU 8i dies together, doubling compute performance and HBM bandwidth to overcome memory walls during multi-turn agent workloads.

3. 20:59
   The DecoderSelected

   Google Unveils TPU 8tx and TPU 8i Max, Delivering Four TPU Systems Within a Single Year

   Google has expanded its eighth-generation AI accelerator lineup with two new system configurations—TPU 8tx and TPU 8i Max—marking the first time the company has shipped four TPU variants within a single year. TPU 8tx is designed for confidential computing, keeping data and model weights encrypted and isolated throughout computation. TPU 8i Max integrates two chips into a single package, doubling compute capacity, memory, and bandwidth within the same rack footprint.

4. 20:43
   IT之家 · AI 筛选Selected

   Google Unveils TPU 8tx and TPU 8i Max Chips

   Google announced an expansion of its AI chip lineup with two new processors—TPU 8tx and TPU 8i Max—both expected to hit the market next year. The TPU 8tx works alongside AMD chips to deliver chip-level data encryption, targeting confidential computing needs in government and strictly regulated industries. Meanwhile, the TPU 8i Max adopts a dual-chiplet design in a single package to boost memory and compute capacity for ultra-long context windows. Google's TPUs have already secured purchases or partnership agreements from customers including Apple, Meta, Oracle, and Anthropic.

Current heat 49·Comparable peak 59（Nov 10 06:00）·Comparable change, last 24 hours–

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.