MoEZip2 min read
MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs
Mixture-of-Experts (MoE) language models scale model capacity efficiently by activating a small subset of parameters per token. However, in long-context inference, memory remains a major bottleneck because the KV cache grows linearly with sequence length.
By Minsang Kim, Seungjun BaekarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 23, 2026.
Comments
Sign in to join the discussion.