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

arXiv: https://arxiv.org/abs/2609.12399 · HTML: https://mlsanity.com/paper/2609.12399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration](https://mlsanity.com/paper/2406.14017/) (2024)
- [PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations](https://mlsanity.com/paper/2510.07784/) (2025)
- [OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search](https://mlsanity.com/paper/2509.03236/) (2025)
- [Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer](https://mlsanity.com/paper/2602.23978/) (2026)
- [xGR: Efficient Generative Recommendation Serving at Scale](https://mlsanity.com/paper/2512.11529/) (2025)
- [S-GRec: Personalized Semantic-Aware Generative Recommendation with Asymmetric Advantage](https://mlsanity.com/paper/2602.10606/) (2026)
- [HoloRec: Holistic Encoding and Interleaved Reasoning for Generative Recommendation](https://mlsanity.com/paper/2606.15331/) (2026)

## Built on by (most cited first, 1 of 1)

- [LumoTree: Path-Parallel Speculative Verification for Hybrid Language Models](https://mlsanity.com/paper/2609.23900/) (2026)

## Abstract (arXiv)

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 transitions. Using this representation, OneLA computes only the state information required at each decoding step, without reconstructing a full recurrent state for every beam. Furthermore, OneLA uses a lightweight ancestry index to track the transition records that make up each beam's history, allowing beams to be updated without moving or copying existing records. A fused GPU kernel further reuses the shared state across beams. Our analysis shows that OneLA achieves 1.54-2.46x end-to-end decode speedups while substantially reducing recurrent-state memory use and data movement.