SOURCE-LINKED INTELLIGENCE

OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Generative recommendation (GR) relies on large-beam decoding to generate hundreds of candidate items, creating a new scaling challenge for recurrent linear attention. Existing linear attention serving systems either materialize a full recurrent state for every beam or repeatedly replay shared history, incurring substantial memory and traffic overhead. To address this, we present OneLA, a linear-attention decoding framework that exploits the shared prompt and short divergent suffixes of GR workloads. Specifically, OneLA represents all beam states using a single shared prompt-derived state and c

Read original source ↗ Open in workspace

recordType

paper

region

Global