Google expands 8th-gen TPU lineup with TPU 8i Max and TPU 8tx, four systems in one generation
rakyll · x · 2026-11-09
Google's AI & Infrastructure team (Amin Vahdat) announced two new additions to its 8th-generation TPU portfolio: TPU 8i Max for massive context windows and highest per-rack compute density, and TPU 8tx for secure, confidential inference — the first time four distinct TPU systems ship in a single generation within one year.
Software-stack updates announced alongside:
- Native PyTorch & Hugging Face model support via TorchTPU, with zero code rewrites
- Open-source TPU Sync cutting KV transfer latency by >90%
- Agent Compute Engine to eliminate idle compute waste
More from Infra
- Impatient waiting for the electrician, ML engineer grabs a few B200s from Lambda — TheZachMueller · 2026-11-09
- Google launches two new TPU variants to challenge Nvidia, reportedly ~30% cheaper — CurieuxExplorer · 2026-11-09
- NVIDIA, Rebellions and SK Telecom partner on Korea's sovereign AI infrastructure — pstAsiatech · 2026-11-09
- DHH: Omarchy 4.6 auto-picks best local models, AMD 495 runs Flash Next impressively — AnushElangovan · 2026-11-09
- LowRAM: Huawei's KV cache compression gets 4x near-lossless value amortisation — Teresa Delgado · 2026-11-09
- Autopilot for CI launches: adaptive multi-provider runner routing cuts bills 30% — emeka_boris · 2026-11-09