#01
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models
Sparse mixture-of-experts (MoE) layers expand recommendation capacity through conditional computation, yet a trained checkpoint still stores and routes over its full expert bank. We study a deployment problem: convert th
推荐理由UniMoMo: Expert Merging-Based MoE：Sparse mixture-of-experts (MoE) layers expand recommendation capacity through。