paper-with-me

Papers

Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management

2025-04-19 · Hang Zhang, Jiuchen Shi, Yixiao Wang, Quan Chen, Yizhou Shan, Minyi Guo

Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accelerations can improve inference performance. However, existing Multi-LoRA inference systems fail to optimize serving performance like Time-To-First-Toke (TTFT), neglecting usage dependencies when caching LoRAs and KVs. We therefore propose FASTLIBRA, a Multi-LoRA caching system to optimize the serving performance. FASTLIBRA comprises a dependency-aware cache manager and a performance-driven cache swapper. The cache manager maintains the usage dependencies between LoRAs and KV caches during the inference with a unified caching pool. The cache swapper determines the swap-in or out of LoRAs and KV caches based on a unified cost model, when the HBM is idle or busy, respectively. Experimental results show that ELORA reduces the TTFT by 63.4% on average, compared to state-of-the-art works.

📄 PDF Abstract BibTeX arXiv:2505.03756

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelManagement

Similar Papers 제목 키워드 기반

PLoRA: Efficient Concurrent LoRA Training for Large Language Models

2025-08-04 · Minghao Yan, Zhuang Wang, Zhen Jia, Shivaram Venkataraman 외 arxiv

Low-Rank Adaptation (LoRA) has gained popularity as a fine-tuning approach for Large Language Models (LLMs) due to its low resource requirements and good performance. While numerous studies have investigated ways to impr…

Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead

2024-06-17 · Rickard Brüel-Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen 외

Fine-tuning large language models (LLMs) with low-rank adaptations (LoRAs) has become common practice, often yielding numerous copies of the same LLM differing only in their LoRA updates. This paradigm presents challenge…

GPUModel Compression

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

2023-11-06 · Ying Sheng, Shiyi Cao, Dacheng Li, Coleman Hooper 외

The "pretrain-then-finetune" paradigm is commonly adopted in the deployment of large language models. Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method, is often employed to adapt a base model to a mul…

GPUparameter-efficient fine-tuning

Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA

2025-11-26 · Allison Li, Kristjan Greenewald, Thomas Parnell, Navid Azizan arxiv

Modern large language model (LLM) systems increasingly rely on multi-turn pipelines that are composed of multiple task-specific adapters, yet existing serving frameworks remain inefficient, incurring substantial recomput…

Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving

2025-10-30 · Yuchen Zhang, Hanyue Du, Chun Cao, Jingwei Xu arxiv

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning (PEFT) technique for adapting large language models (LLMs) to downstream tasks. While prior work has explored strategies for integrat…

parameter-efficient fine-tuning