OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching Paper • 2608.08097 • Published 5 days ago • 24
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving Paper • 2607.00466 • Published Jul 1 • 32
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving Paper • 2607.00466 • Published Jul 1 • 32