Zyphra
@ZyphraAI
Full stack open superintelligence
加入 March 2021
40 正在关注 14.9K 粉丝
In Mixture of Expert (MoE) models the cost of moving tokens to their experts can dominate total runtime.
At Zyphra research, we use patterns in how tokens are routed to experts to make that communication faster by up to 2.63x on @AMD MI300X GPUs, with the model unchanged.
显示更多
