A Decoding Acceleration Framework for Industrial Deployable LLM-based Recommender Systems

• URL: http://arxiv.org/abs/2408.05676v1
• Date: Sun, 11 Aug 2024 02:31:13 GMT
• Title: A Decoding Acceleration Framework for Industrial Deployable LLM-based Recommender Systems
• Authors: Yunjia Xi, Hangyu Wang, Bo Chen, Jianghao Lin, Menghui Zhu, Weiwen Liu, Ruiming Tang, Weinan Zhang, Yong Yu,
• Abstract summary: We propose a Decoding Acceleration Framework for LLM-based Recommendation (dubbed DARE), with Customized Retrieval Pool to improve retrieval efficiency and Relaxed Verification to increase the acceptance rate of draft tokens. DARE has been deployed to online advertising scenarios within a large-scale commercial environment, achieving a 3.45x speedup while maintaining the downstream performance.
• Score: 49.588316022381385
• License:
• Abstract: Recently, increasing attention has been paid to LLM-based recommender systems, but their deployment is still under exploration in the industry. Most deployments utilize LLMs as feature enhancers, generating augmentation knowledge in the offline stage. However, in recommendation scenarios, involving numerous users and items, even offline generation with LLMs consumes considerable time and resources. This generation inefficiency stems from the autoregressive nature of LLMs, and a promising direction for acceleration is speculative decoding, a Draft-then-Verify paradigm that increases the number of generated tokens per decoding step. In this paper, we first identify that recommendation knowledge generation is suitable for retrieval-based speculative decoding. Then, we discern two characteristics: (1) extensive items and users in RSs bring retrieval inefficiency, and (2) RSs exhibit high diversity tolerance for text generated by LLMs. Based on the above insights, we propose a Decoding Acceleration Framework for LLM-based Recommendation (dubbed DARE), with Customized Retrieval Pool to improve retrieval efficiency and Relaxed Verification to increase the acceptance rate of draft tokens, respectively. Extensive experiments demonstrate that DARE achieves a 3-5x speedup and is compatible with various frameworks and backbone LLMs. DARE has also been deployed to online advertising scenarios within a large-scale commercial environment, achieving a 3.45x speedup while maintaining the downstream performance.

Related papers

• Efficient Inference for Large Language Model-based Generative Recommendation [78.38878421030522]
  Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly. Applying Speculative Decoding (SD) to generative recommendation presents unique challenges due to the requirement of generating top-K items. We propose an alignment framework named AtSpeed, which presents the AtSpeed-S optimization objective for top-K alignment under the strict top-K verification.
  arXiv  Detail & Related papers  (2024-10-07T16:23:36Z)
• LARR: Large Language Model Aided Real-time Scene Recommendation with Semantic Understanding [19.510385758079966]
  Large Language Model Aided Real-time Scene Recommendation(LARR) This paper introduces Large Language Model Aided Real-time Scene Recommendation(LARR)
  arXiv  Detail & Related papers  (2024-08-21T10:56:26Z)
• Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models [53.547190001324665]
  We propose REKI to acquire two types of external knowledge about users and items from large language models (LLMs) We develop individual knowledge extraction and collective knowledge extraction tailored for different scales of scenarios, effectively reducing offline resource consumption. Experiments demonstrate that REKI outperforms state-of-the-art baselines and is compatible with lots of recommendation algorithms and tasks.
  arXiv  Detail & Related papers  (2024-08-20T03:45:24Z)
• VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework [10.716259527813522]
  Large Language Model (LLM) has gained significant popularity and is extensively utilized across various domains. Most LLM deployments occur within cloud data centers, where they encounter substantial response delays and incur high costs. Leveraging vector database caching to store LLM request results at the edge can substantially mitigate response delays and cost associated with similar requests.
  arXiv  Detail & Related papers  (2024-06-19T09:41:37Z)
• New Solutions on LLM Acceleration, Optimization, and Application [14.995654657013741]
  Large Language Models (LLMs) have become extremely potent instruments with exceptional capacities for comprehending and producing human-like text in a range of applications. However, the increasing size and complexity of LLMs present significant challenges in both training and deployment. We provide a review of recent advancements and research directions aimed at addressing these challenges.
  arXiv  Detail & Related papers  (2024-06-16T11:56:50Z)
• One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
  Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
  arXiv  Detail & Related papers  (2024-05-30T03:44:54Z)
• Improve Temporal Awareness of LLMs for Sequential Recommendation [61.723928508200196]
  Large language models (LLMs) have demonstrated impressive zero-shot abilities in solving a wide range of general-purpose tasks. LLMs fall short in recognizing and utilizing temporal information, rendering poor performance in tasks that require an understanding of sequential data. We propose three prompting strategies to exploit temporal information within historical interactions for LLM-based sequential recommendation.
  arXiv  Detail & Related papers  (2024-05-05T00:21:26Z)
• Inference with Reference: Lossless Acceleration of Large Language Models [97.04200102556551]
  LLMA is an accelerator to speed up Large Language Model (LLM) inference with references. It is motivated by the observation that there are abundant identical text spans between the decoding result by an LLM and the reference that is available in many real world scenarios.
  arXiv  Detail & Related papers  (2023-04-10T09:55:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.