MoE Expert Pruning
Cross-source consensus on MoE Expert Pruning from 1 sources and 4 claims.
1 sources · 4 claims
How it works
Comparisons
Highlighted claims
- RCO outperformed EvoESAP on Qwen3-30B-A3B at both 25% and 50% sparsity while taking less time. — Budget Constraints as Riemannian Manifolds
- Calibration data strongly determines which capabilities survive expert pruning. — Budget Constraints as Riemannian Manifolds
- On OLMoE-1B-7B, RCO exceeded EvoESAP after 50 steps and improved further by 300 steps. — Budget Constraints as Riemannian Manifolds
- RCO searches a larger pruning space than layer-count evolutionary allocation because it can choose both how many and which experts to prune. — Budget Constraints as Riemannian Manifolds