paper-with-me

홈 › Papers

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding

2025-01-21 · Zikun Li, Zhuofu Chen, Remi Delacourt, Gabriele Oliaro, Zeyu Wang, Qinghan Chen, Shuhuai Lin, April Yang, Zhihao Zhang, Zhuoming Chen, Sean Lai, Xinhao Cheng, Xupeng Miao, Zhihao Jia

Modern large language model (LLM) applications exhibit diverse service-level objectives (SLOs), from low-latency requirements in interactive coding assistants to more relaxed constraints in data wrangling tasks. Existing LLM serving systems, which rely on uniform batching and scheduling strategies, often fail to meet these heterogeneous SLOs concurrently. We present AdaServe, the first LLM serving system designed to support efficient multi-SLO serving through SLO-customized speculative decoding. AdaServe formulates multi-SLO serving as a constrained optimization problem and introduces a hardware-aware algorithm that constructs a speculation tree tailored to each request's latency target. It features a speculate-select-verify pipeline that enables fine-grained control over decoding speed while maximizing system throughput. AdaServe further adapts to workload variation by dynamically adjusting speculation parameters. Evaluations across diverse workloads show that AdaServe reduces SLO violations by up to 4.3$\times$ and improves goodput by up to 1.9$\times$ compared to the best performing baselines, highlighting its effectiveness in multi-SLO serving.

📄 PDF Abstract BibTeX arXiv:2501.12162

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelScheduling

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

Accelerating LLM Inference with Staged Speculative Decoding

2023-08-08 · Benjamin Spector, Chris Re

Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We addre…

ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding

2026-04-15 · Heming Xia, Yongqi Li, Cunxiao Du, Mingbo Song 외 arxiv

Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM capabilities advance, effective tool use increasingly involves multi…

SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

2023-05-16 · Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng 외

This paper introduces SpecInfer, a system that accelerates generative large language model (LLM) serving with tree-based speculative inference and verification. The key idea behind SpecInfer is leveraging small speculati…

DecoderLanguage ModelingLanguage ModellingLarge Language Model

XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding

2025-07-31 · Dian Chen, Yansong Qu, Xinyang Li, Ming Li 외 arxiv

Current auto-regressive models can generate high-quality, topologically precise meshes; however, they necessitate thousands-or even tens of thousands-of next-token predictions during inference, resulting in substantial l…

DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification

2026-04-08 · Ziyi Wang, Siva Rajesh Kasa, Ankith M S, Santhosh Kumar Kasa 외 arxiv

Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that str…