Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #30714

TPU 8tx

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

CODING · 1 SOURCE · InfoQ AI, ML & Data Engineering

Google open-sources 'TPU Sync' C++ library to move KV cache and weights on TPUs

Google Cloud released TPU Sync, a native C++ library (Apache 2.0) that moves KV cache blocks and model weights between TPU HBM, host DRAM, shared storage, and the network, with Python wheels for JAX and PyTorch. Google reports large latency and TTFT reductions for long-context and disaggregated LLM serving (e.g., Qwen3 235B median KV transfer latency down to ~230 ms and average TTFT reductions of ~60%, up to 90% for a 480B model), but several features (storage tier, RL weight sync) and Python packages are experimental or development builds and APIs may change rapidly.

7.0

COMPANIES · 3 SOURCES · Google · The Decoder · TechCrunch AI

Google adds TPU 8tx and TPU 8i Max to 8th‑generation TPU portfolio

Google expanded its eighth‑generation TPU lineup with two new systems: TPU 8tx, designed for secure/confidential inference (paired with 5th‑Gen AMD EPYC hosts and the low‑latency Boardfly network) and TPU 8i Max, built for massive context windows and highest compute density per rack. The announcement brings the generation to four systems (TPU 8t, 8i, 8tx, 8i Max), targeting agentic workloads, regulated enterprises, and large‑context reasoning.

8.0