2 papers
cs.LG2026
RankLane: Efficient MoE Prefill on Accelerators with Ranked Expert Capacities
Wentao Ni, Chihao Yu, Hong Cai +4
Mixture-of-experts (MoE) models expand model capacity by activating only a subset of experts for each token. On accelerators with static execution plans, expert capacities and plac…
cs.LG2026
TileWeave: Heterogeneous Tiling for Sparse Prefill on Mobile SoCs
Wentao Ni, Hong Cai, Mingu Lee +7
Smartphone applications increasingly require large language models to process long contexts, whereas high prefill latency and memory demands constrain local inference. Block-sparse…