高通徐晧亮相WAIC端侧AI论坛：从智能体需求出发，持续推动计算架构创新
Quick Answer
At the WAIC forum, Qualcomm's Dr.
Quick Take
Xu Haoliang emphasized the transformative potential of , highlighting a tenfold increase in token processing needs for devices. He introduced new architectures designed for continuous online workloads and collaboration with partners like Mianbi to enhance edge model capabilities.
Key Points
- Token processing needs for edge devices are increasing from thousands to millions.
- Qualcomm's new architectures target continuous online workloads and sensor data processing.
- Edge models may match cloud model capabilities in the next 1-2 years.
- Qualcomm's 5G/6G connectivity is crucial for seamless edge-cloud collaboration.
- The Snapdragon 8 Gen 2 platform supports advanced edge AI applications.
Source Excerpt
From the original publisher, up to about 700 characters7月19日，2026年世界人工智能大会正在进行中，高通公司全球副总裁、中国区研发负责人、IEEE Fellow徐晧博士出席“端侧AI创新和行业发展论坛”，并发表
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from 雷峰网芯片
See more →Token账单迷雾：当每百万Token多少钱变成「比价陷阱」
The rise of Token billing in AI has transformed costs into operational expenses, with prices varying significantly due to factors like model efficiency, energy costs, and contract terms. As companies shift from GPU hours to Token-based billing, understanding the hidden complexities behind Token pricing becomes crucial for effective budgeting.
