2 papers
cs.LG2026
ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference
Xiongwei Zhu, Xiaojian Liao, Tianyang Jiang +3
Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, reducing activated computation while maintaining high model capacity. However, in…
cs.AR2026
Nemo: A Low-Write-Amplification Cache for Tiny Objects on Log-Structured Flash Devices
Xufeng Yang, Tingting Tan, Jingxin Hu +7
Modern storage systems predominantly use flash-based SSDs as a cache layer due to their favorable performance and cost efficiency. However, in tiny-object workloads, existing flash…