paper-with-me

Papers

REST: Retrieval-Based Speculative Decoding

2023-11-14 · Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D. Lee, Di He

We introduce Retrieval-Based Speculative Decoding (REST), a novel algorithm designed to speed up language model generation. The key insight driving the development of REST is the observation that the process of text generation often includes certain common phases and patterns. Unlike previous methods that rely on a draft language model for speculative decoding, REST harnesses the power of retrieval to generate draft tokens. This method draws from the reservoir of existing knowledge, retrieving and employing relevant tokens based on the current context. Its plug-and-play nature allows for seamless integration and acceleration of any language models, all without necessitating additional training. When benchmarked on 7B and 13B language models in a single-batch setting, REST achieves a significant speedup of 1.62X to 2.36X on code or text generation. The code of REST is available at https://github.com/FasterDecoding/REST.

📄 PDF Abstract BibTeX arXiv:2311.08252

Code (1)

fasterdecoding/rest 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingRetrievalText Generation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

CREST: Effectively Compacting a Datastore For Retrieval-Based Speculative Decoding

2024-08-08 · Sophia Ho, Jinsol Park, Patrick Wang

We present CREST (Compact Retrieval-Based Speculative Decoding), a redesign of REST that allows it to be effectively "compacted". REST is a drafting technique for speculative decoding based on retrieving exact n-gram mat…

HumanEvalRetrieval

DReSD: Dense Retrieval for Speculative Decoding

2025-02-21 · Milan Gritta, Huiyin Xue, Gerasimos Lampouras

Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while…

Language ModelingLanguage ModellingLarge Language ModelRetrieval

RASD: Retrieval-Augmented Speculative Decoding

2025-03-05 · Guofeng Quan, Wenfeng Feng, Chuzhan Hao, Guochao Jiang 외

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or addit…

Retrieval

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

2024-08-11 · Yunjia Xi, Hangyu Wang, Bo Chen, Jianghao Lin 외

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…

Recommendation SystemsRetrieval

Nearest Neighbor Speculative Decoding for LLM Generation and Attribution

2024-05-29 · Minghan Li, Xilun Chen, Ari Holtzman, Beidi Chen 외

Large language models (LLMs) often hallucinate and lack the ability to provide attribution for their generations. Semi-parametric LMs, such as kNN-LM, approach these limitations by refining the output of an LM for a give…

Language ModelingLanguage ModellingRetrieval