paper-with-me

Papers

Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens

2024-02-24 · Ziqian Zeng, Jiahong Yu, Qianshi Pang, ZiHao Wang, Huiping Zhuang, HongEn Shao, Xiaofeng Zou

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their widespread application is hindered by the resource-intensive decoding process. To address this challenge, current approaches have incorporated additional decoding heads to enable parallel prediction of multiple subsequent tokens, thereby achieving inference acceleration. Nevertheless, the accuracy of these decoding heads falls short of the auto-regressive decoding approach. In light of these limitations, we propose Chimera, a novel framework specifically designed for speculative sampling. Within this framework, we introduce a lightweight draft model that effectively utilizes previously generated tokens to predict subsequent words. To ensure both accuracy and efficiency, we present two strategies within the lightweight draft model. Firstly, we focus on capturing short-range dependencies at the bottom layer. Secondly, we leverage the readily available representations from the original LLM.Through empirical evaluation on the Vicuna and LlaMA-2 series, Chimera demonstrates impressive results, achieving an average latency speedup ratio of 2.7x compared to the vanilla auto-regressive decoding approach. This highlights the potential of our proposed framework in significantly improving the efficiency of large language models during the decoding process.

📄 PDF Abstract BibTeX arXiv:2402.15758

Code (0)

등록된 구현이 없습니다.

Tasks

All

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Chimera Chimera is a pipeline model parallelism scheme which combines bidirectional pipelines for efficiently training large-scale models. The key idea of Chimera is to combine two…

Similar Papers 제목 키워드 기반

Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies

2025-01-31 · Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky 외

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single targe…

Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding

2025-02-08 · Sukmin Cho, Sangjin Choi, Taeho Hwang, Jeongyeon Seo 외

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gaine…

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

2024-02-19 · Hanling Yi, Feng Lin, Hongbin Li, Peiyang Ning 외

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 i…

HumanEvalLanguage ModelingLanguage ModellingLarge Language Model

Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding

2023-09-15 · Jun Zhang, Jue Wang, Huan Li, Lidan Shou 외

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and v…

Language ModelingLanguage ModellingLarge Language Model

AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures

2024-12-25 · Situo Zhang, Hankun Wang, Da Ma, Zichen Zhu 외

Speculative Decoding (SD) is a popular lossless technique for accelerating the inference of Large Language Models (LLMs). We show that the decoding speed of SD frameworks with static draft structures can be significantly…