Our newest TPUs: 8tx and 8i Max, built for the agentic era
meetpateltech
27 points
4 comments
November 09, 2026
Related Discussions
Found 5 related stories in 122.6ms across 12,324 title embeddings via pgvector HNSW
- TPU 8tx and TPU 8i Max _benx_ · 239 pts · November 09, 2026 · 87% similar
- OpenTPU – An open-source AI accelerator, developed by AI fsbonetto · 267 pts · October 06, 2026 · 58% similar
- Google open-sources TorchTPU, a native PyTorch back end for TPUs ilreb · 309 pts · October 20, 2026 · 57% similar
- Advancing the price-performance frontier with GPT‑5.6 tedsanders · 541 pts · July 30, 2026 · 49% similar
- OpenAI claims its new chips can outperform Nvidia processors in tests TravisJamison · 16 pts · August 25, 2026 · 48% similar
Discussion Highlights (3 comments)
gniv
Seems like a big deal, but there's nothing about availability. They might say more during the broadcast later today.
pierreb-aiva
> 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
xnx
More bad news for Nvidia today.