Global AI Chip Summit 2026: from TOPS to tokens as agents reshape silicon
The 2026 Global AI Chip Summit in Shanghai brought together more than 60 speakers across an opening session and three forums on large-model AI chips, agent inference chips and embodied-intelligence chips, focused on the computing chain from TOPS to tokens — covering architecture innovation, 3D stacking and near-memory compute, KV cache, new memory types, compute-in-memory, analog computing, RISC-V and token-factory operations. Several vendors used the stage to preview or detail products: Houmo AI said its M50 chip has reached 150+ design wins in half a year of mass production and that its next flagship A20 has taped out; Intel previewed a high-density cabinet with 128 or 192 Granite Rapids processors that it says can run 50,000 concurrent agents; Maitech said its 3D TPU has taped out and is expected back in November. Those figures are vendor claims and have not been independently verified.
The summit reflects a shift in AI chip competition from raw peak TOPS toward system-level co-design of compute, memory, interconnect and software, with agent inference and embodied intelligence emerging as new sources of silicon demand.