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

arXiv cs.AISeptember 14, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2609.12399v1 Announce Type: new Abstract: 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 compact, append-only records of their divergent trans

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning