Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems
Low-Rank Adaptation (LoRA) has become the de facto method for parameter-efficient fine-tuning of large language models (LLMs), enabling rapid adaptation to diverse domains. In production, LoRA-based models are served at scale, creating multi-tenant environments with hundreds of adapters sharing a base model. However, state-of-the-art serving systems co-batch heterogeneous adapters without accounting for rank (size) variability, leading to severe performance skew, which ultimately requires adding more GPUs to satisfy service-level objectives (SLOs). Existing optimizations, focused on loading, caching, and kernel execution, ignore this heterogeneity, leaving GPU resources underutilized. We present LoRAServe, a workload-aware dynamic adapter placement and routing framework designed to tame rank diversity in LoRA serving. By dynamically rebalancing adapters across GPUs and leveraging GPU Direct RDMA for remote access, LoRAServe maximizes throughput and minimizes tail latency under real-world workload drift. Evaluations on production traces from Company X show that LoRAServe elicits up to 2$\times$ higher throughput, up to 9$\times$ lower TTFT, while using up to 50% fewer GPUs under SLO constraints compared to state-of-the-art systems.
Code (0)
등록된 구현이 없습니다.
Tasks
parameter-efficient fine-tuningSimilar Papers 제목 키워드 기반
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
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-tuningtLoRA: Efficient Multi-LoRA Training with Elastic Shared Super-Models
As Low-Rank Adaptation (LoRA) becomes the standard approach for efficiently fine-tuning large language models (LLMs), shared clusters increasingly execute many concurrent LoRA training jobs over the same frozen backbone.…
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
The rapid development of Large Language Models (LLMs) has been pivotal in advancing AI, with pre-trained LLMs being adaptable to diverse downstream tasks through fine-tuning. Federated learning (FL) further enhances fine…
Federated LearningPrivacy PreservingImproving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management
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 accel…
Language ModelingLanguage ModellingLarge Language ModelManagementV-LoRA: An Efficient and Flexible System Boosts Vision Applications with LoRA LMM
Large Multimodal Models (LMMs) have shown significant progress in various complex vision tasks with the solid linguistic and reasoning capacity inherited from large language models (LMMs). Low-rank adaptation (LoRA) offe…