{"rewrite":{"id":"r_b5c16ebfcc12c02dfc4259c0","clusterId":"c_55a341433c8f1117f4cb2e3a","slug":"google-adds-tpu-8tx-and-tpu-8i-max-to-eighth-generation-tpu-lineup","model":"deepseek-v4-1-flash","headline":"Google Adds TPU 8tx and TPU 8i Max to Eighth-Generation TPU Lineup","summary":"Google announced two additions to its eighth-generation TPU lineup on November 9, 2026: TPU 8tx and TPU 8i Max. TPU 8tx pairs the TPU 8t chip with AMD's 5th-generation EPYC processor as host CPU and protects confidential data at the hardware level, with Boardfly networking cutting latency by up to half. TPU 8i Max combines two TPU 8i chips in one package to handle large context windows.","whyItMatters":"Google is answering the spread of AI agents by building systems around existing TPU chips rather than new silicon, splitting the eighth generation between confidential-data processing and large-context inference.","webCardHtml":"\u003cp\u003eGoogle is not designing new silicon for either system. TPU 8tx uses the same chip as TPU 8t and adds AMD\u0026#39;s 5th-generation EPYC processor as host CPU, plus hardware-level protection and isolation of data and model weights while AI is processing. The Boardfly low-latency networking technology cuts processing latency by up to half versus TPU 8t, with almost no performance impact, according to the company. TPU 8tx also handles small-scale training, distillation, and reinforcement learning, so companies can tune models without moving confidential data elsewhere.\u003c/p\u003e\u003cp\u003eTPU 8i Max is aimed at AI that reads widely while it works. Memory transfer speed limits processing when an AI must pull huge amounts of data, as with entire codebases or several hours of video, so the system pairs two TPU 8i chips in a single package. The eighth-generation lineup now holds four entries: TPU 8t, TPU 8i, TPU 8tx, and TPU 8i Max.\u003c/p\u003e\u003cul\u003e\u003cli\u003e\u003cstrong\u003eTPU 8tx\u003c/strong\u003e: Uses the TPU 8t chip with AMD 5th-generation EPYC host CPU; protects confidential data and model weights at hardware level; Boardfly networking cuts latency by up to half versus TPU 8t.\u003c/li\u003e\u003cli\u003e\u003cstrong\u003eTPU 8i Max\u003c/strong\u003e: Combines two TPU 8i chips in a single package for AI that references large amounts of information.\u003c/li\u003e\u003c/ul\u003e","blueskyPost":"TPU 8tx puts an AMD EPYC chip inside a Google TPU system. Hardware-level data protection depends on a host CPU Google does not make.","twitterPost":"TPU 8tx runs on an AMD EPYC host CPU, so Google's confidential-data protection rides on a chip it does not build.","threadsPost":"TPU 8tx protects confidential data at the hardware level, and the host CPU doing that work is AMD's 5th-generation EPYC. Google's privacy claim depends on silicon from a company it competes with in data center chips.","newsletterBlurb":"Google announced TPU 8tx and TPU 8i Max on November 9, 2026, bringing the eighth-generation TPU lineup to four systems. TPU 8tx uses the TPU 8t chip with AMD's 5th-generation EPYC host CPU and hardware-level protection for confidential data, while TPU 8i Max combines two TPU 8i chips in one package. Google built both around existing chips rather than new designs.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20261110-google-tpu-8i-max-8tx/\",\"title\":\"Google announces new AI chips \\\"TPU 8tx\\\" and \\\"TPU 8i Max\\\": a confidential-information-protection model using AMD CPUs and a model with twice the processing performance\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":5548,"outputTokens":1017,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1794291495,"createdAt":"2026-11-10T06:12:59.000Z","publishedAt":"2026-11-10T06:17:10.000Z","updatedAt":"2026-11-10T06:17:10.000Z"},"cluster":{"id":"c_55a341433c8f1117f4cb2e3a","canonicalTitle":"Googleが新型AIチップ「TPU 8tx」「TPU 8i Max」を発表、AMD製CPUを採用した機密情報保護モデルと処理性能2倍のモデルが登場","representativeArticleId":"a_b73d4d2aabd0c8152c83609d","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[],\"studios\":[],\"people\":[],\"type\":\"news\",\"domain\":\"industry\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-11-10T05:40:00.000Z","lastSeenAt":"2026-11-10T05:40:00.000Z","updatedAt":"2026-11-10T06:17:10.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20261110-google-tpu-8i-max-8tx/","title":"Googleが新型AIチップ「TPU 8tx」「TPU 8i Max」を発表、AMD製CPUを採用した機密情報保護モデルと処理性能2倍のモデルが登場"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":[],"studios":[],"people":[],"type":"news","domain":"industry","is_roundup":false},"keyFacts":["Google announced TPU 8tx and TPU 8i Max on November 9, 2026.","TPU 8tx uses the same chip as TPU 8t and combines it with AMD's 5th-generation EPYC processor as host CPU.","TPU 8tx reduces processing latency by up to half compared with TPU 8t through the Boardfly networking technology.","TPU 8i Max combines two TPU 8i chips into a single package.","The eighth-generation TPU lineup now has four types: TPU 8t, TPU 8i, TPU 8tx, and TPU 8i Max."],"pageLinks":{"healthSlugs":[],"storySlugs":[],"entities":[],"stories":[],"entitiesOk":true,"storiesOk":true}}