6 papers
PLoRA: Efficient Concurrent LoRA Training for Large Language Models
Minghao Yan, Zhuang Wang, Zhen Jia +2
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 numerou…
The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers
Yifan Lu, Qiyue Zhang, Shenrun Zhang +4
LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by dynamically selecting a model for each query. Recent work has explored a broad ra…
ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads
Jingwei Zuo, Xinze Feng, Zien Liu +5
Low-Rank Adaptation (LoRA) is now the dominant method for parameter-efficient fine-tuning of large language models, but achieving a high-quality adapter often requires systematic h…
ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management
Zaifeng Pan, Yipeng Shen, Zhengding Hu +6
LLM-based multi-agent simulations are increasingly adopted across application domains, but remain difficult to scale due to GPU memory pressure. Each agent maintains private GPU-re…
Lazarus: Resilient and Elastic Training of Mixture-of-Experts Models
Yongji Wu, Wenjie Qu, Xueshen Liu +10
Sparsely-activated Mixture-of-Experts (MoE) architecture has increasingly been adopted to further scale large language models (LLMs). However, frequent failures still pose signific…
Marconi: Prefix Caching for the Era of Hybrid LLMs
Rui Pan, Zhuang Wang, Zhen Jia +5
Hybrid models that combine the language modeling capabilities of Attention layers with the efficiency of Recurrent layers (e.g., State Space Models) have gained traction in practic…