SemiAnalysis· @SemiAnalysis_ · X·· 3 小时前AI 评分31
AI 导读
GLM 5.3 值得拉响警报吗?🚨 “只要你有预算,它写 kernel 会比人类更快。” Kimbo(@kimbochen)和 Wenyao(@gao_wenyao)本周与 Jordan(@JordanNanos)一起解析稀疏注意力、无人定价的内存瓶颈,以及为什么更便宜的 token 可能意味着更多 HBM,而非更少。
正文
Is GLM 5.3 worth sounding the alarms? 🚨
“As long as you have the budget, it will write faster kernels than humans.”
Kimbo (@kimbochen) and Wenyao (@gao_wenyao) join Jordan (@JordanNanos) this week to unpack sparse attention, the memory bottleneck nobody’s pricing in, and why cheaper tokens might mean more HBM, not less.
来源:SemiAnalysis · x.com