conftrace_

expert load balancing

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

mixture of expert (3) model compression (2) dynamic gating (1) model deployment (1) parallel computation (1) expert routing (1) model efficiency (1) flops reduction (1) neural network (1) token dropping (1)

Papers

AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models EMNLP 2024 Toward Efficient Inference for Mixture of Experts NeurIPS 2024 Turn Waste into Worth: Rectifying Top-k Router of MoE EMNLP 2024