Zyphra
@ZyphraAI
Full stack open superintelligence
参加 March 2021
40 フォロー中 14.9K ファン
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.
もっと見る
