paper-with-me

Papers

Speculative Decoding Scaling Laws (SDSL): Throughput Optimization Made Simple

2026-02-25 · Amirhossein Bozorgkhoo, Igor Molybog arxiv

Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can be costly. This study of spec- ulative decoding proposes a theory that ana- lytically connects the key hyperparameters of pre-trained LLMs to the throughput efficiency of a downstream SD-based inference system. The theory allows the prediction of throughput- optimal hyperparameters for the components of an inference system before their pre-training.

📄 PDF Abstract BibTeX arXiv:2603.11053

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scaling Laws for Speculative Decoding

2025-05-08 · Siyuan Yan, Mo Zhu, Guo-qing Jiang, Jianfei Wang 외

The escalating demand for efficient decoding in large language models (LLMs) is particularly critical for reasoning-intensive architectures like OpenAI-o3 and DeepSeek-R1, which depend on extended chain-of-thought reason…

PRISM: Parametrically Refactoring Inference for Speculative Sampling Draft Models

2026-02-02 · Xuliang Wang, Yuetao Chen, Maochan Zhen, Fang Liu 외 arxiv

Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerate LLM decoding, attracting attention fro…

Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving

2025-12-27 · Rui Li, Zhaoning Zhang, Libo Zhang, Huaimin Wang 외 arxiv

Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades perform…

SPIRe: Boosting LLM Inference Throughput with Speculative Decoding

2025-04-08 · Sanjit Neelam, Daniel Heinlein, Vaclav Cvicek, Akshay Mishra 외

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding wit…

BASS: Batched Attention-optimized Speculative Sampling

2024-04-24 · Haifeng Qian, Sujan Kumar Gonugondla, Sungsoo Ha, Mingyue Shang 외

Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generativ…

GPUHumanEval