Replacement operators affect training-free MoE expert pruning
Survivors gate scale choice dominates effects in pruning OLMoE, DeepSeek-V2-Lite and Moonlight models; tilted novice operator adds 1.2-1.8% parameters and improves accuracy.
Stories per day · 30 days
1 stories, newest first · one card per story
Stories tagged #moe-expert-pruning