# Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding

arXiv: https://arxiv.org/abs/2408.05676 · HTML: https://mlsanity.com/paper/2408.05676/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2024.

## Built on by (most cited first, 10 of 10)

- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Efficient Inference for Large Language Model-based Generative Recommendation](https://mlsanity.com/paper/2410.05165/) (2024)
- [NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations](https://mlsanity.com/paper/2511.18793/) (2025)
- [MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios](https://mlsanity.com/paper/2603.09983/) (2026)
- [Reinforcement Speculative Decoding for Fast Ranking](https://mlsanity.com/paper/2505.20316/) (2025)
- [From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines](https://mlsanity.com/paper/2604.13468/) (2026)
- [PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation](https://mlsanity.com/paper/2601.16556/) (2026)
- [Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations](https://mlsanity.com/paper/2604.18146/) (2026)
- [Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation](https://mlsanity.com/paper/2604.27747/) (2026)

## Abstract (arXiv)

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers, generating augmented knowledge for downstream tasks. However, in recommendation scenarios with numerous users and items, even offline knowledge generation with LLMs demands significant time and computational resources. This inefficiency arises from the autoregressive nature of LLMs. A promising solution is speculative decoding, a Draft-Then-Verify approach that increases the number of tokens generated per decoding step. In this work, we first identify recommendation knowledge generation as a highly fitting use case for retrieval-based speculative decoding. Then, we discern its two characteristics: (1) the vast number of items and users in RSs leads to retrieval inefficiency, and (2) RSs exhibit high diversity tolerance for LLM-generated text. Building on these insights, we introduce Lossless Acceleration via Speculative Decoding for LLM-based Recommender Systems (LASER), which features a Customized Retrieval Pool to enhance retrieval efficiency and Relaxed Verification to improve the acceptance rate of draft tokens. LASER achieves a 3-5x speedup on public datasets and saves about 67% of computational resources during the online A/B test on a large-scale advertising scenario with lossless downstream recommendation performance. Our code is available at https://github.com/YunjiaXi/LASER