Jul 20, 2026 · Artificial Intelligence

Li Xiuhong on Cross-Cluster Heterogeneous PD Separation and Token Factory “Super Pipeline” at WAIC

The article details how 无问芯穹’s Agentic Infra strategy uses a cross‑cluster heterogeneous PD‑separation architecture (PDD) to cut first‑token latency by 51.5% and token cost by 37.5%, explains the bandwidth bottleneck of KV‑Cache transfer, introduces Decode‑side RadixCache and three‑stage handoff mechanisms, and shows a 37.5% BCR improvement that translates into roughly ten‑fold inference cost reduction.

Agentic InfraCross-ClusterHeterogeneous Computing

0 likes · 25 min read

Li Xiuhong on Cross-Cluster Heterogeneous PD Separation and Token Factory “Super Pipeline” at WAIC

Machine Heart

Apr 25, 2026 · Artificial Intelligence

Jensen Huang Explains Why the Token Factory Is AI’s Ultimate Form

In a 150‑minute interview with Lex Fridman, Nvidia founder Jensen Huang argues that generative AI is turning data centers from storage warehouses into token factories, redefining compute as a production system and outlining the four‑stage Agent Scaling Law that drives this shift.

AI Scaling LawJensen HuangNVIDIA

0 likes · 5 min read

Jensen Huang Explains Why the Token Factory Is AI’s Ultimate Form