conftrace_

top-k routing

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

expert routing (2) mixture of expert (2) sparse moe (1) token routing (1) token dropping (1) large language model (1) load balancing (1) model efficiency (1) parallel computation (1) expert load balancing (1)

Papers

TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice ICLR 2025 Turn Waste into Worth: Rectifying Top-k Router of MoE EMNLP 2024