Skip to content
Sagan

Paper

BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization

Unreadunread

AI summary

arXiv:2606. 00079v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weights must be kept resident in memory.