Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding

Autor:	Yi, Hanling, Lin, Feng, Li, Hongbin, Ning, Peiyang, Yu, Xiaotian, Xiao, Rong
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \textbf{S}mart \textbf{P}arallel \textbf{A}uto-\textbf{C}orrect d\textbf{E}coding (SPACE), an innovative approach designed for achieving lossless acceleration of LLMs. By integrating semi-autoregressive inference and speculative decoding capabilities, SPACE uniquely enables autoregressive LLMs to parallelize token generation and verification. This is realized through a specialized semi-autoregressive supervised fine-tuning process that equips existing LLMs with the ability to simultaneously predict multiple tokens. Additionally, an auto-correct decoding algorithm facilitates the simultaneous generation and verification of token sequences within a single model invocation. Through extensive experiments on a range of LLMs, SPACE has demonstrated inference speedup ranging from 2.7x-4.0x on HumanEval-X while maintaining output quality. Comment: Accepted by ACL 2024 Findings
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.11809 Zobrazit plný text záznamu View this record from Arxiv