paper-with-me

Papers

Inference with Reference: Lossless Acceleration of Large Language Models

2023-04-10 · Nan Yang, Tao Ge, Liang Wang, Binxing Jiao, Daxin Jiang, Linjun Yang, Rangan Majumder, Furu Wei

We propose LLMA, an LLM accelerator to losslessly speed up Large Language Model (LLM) inference with references. LLMA 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 (e.g., retrieved documents). LLMA first selects a text span from the reference and copies its tokens to the decoder and then efficiently checks the tokens' appropriateness as the decoding result in parallel within one decoding step. The improved computational parallelism allows LLMA to achieve over 2x speed-up for LLMs with identical generation results as greedy decoding in many practical generation scenarios where significant overlap between in-context reference and outputs exists (e.g., search engines and multi-turn conversations).

📄 PDF Abstract BibTeX arXiv:2304.04487

Code (2)

microsoft/LMOps/tree/main/llma 공식 구현 jax
niyunsheng/ems-sd pytorch

Tasks

DecoderLanguage ModelingLanguage ModellingLarge Language Model

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

BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models

2024-01-23 · Feng Lin, Hanling Yi, Hongbin Li, Yifan Yang 외

Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency. To mitigate this inefficiency, we present Bi-directional…

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…

LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model

2025-11-07 · Wei Shao, Lingchao Zheng, Pengyu Wang, Peizhen Zheng 외 arxiv

Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through oper…

Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy

2023-12-20 · Yao Zhao, Zhitian Xie, Chen Liang, Chenyi Zhuang 외

As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes cru…

Language ModelingLanguage ModellingLarge Language ModelQuestion Answering+2

CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs

2025-10-30 · Zhiyuan Ning, Jiawei Shao, Ruge Xu, Xinfei Guo 외 arxiv

Speculative decoding has become a widely adopted as an effective technique for lossless inference acceleration when deploying large language models (LLMs). While on-the-fly self-speculative methods offer seamless integra…