English
Related papers

Related papers: Punica: Multi-Tenant LoRA Serving

200 papers

Low-rank adaptation (LoRA) offers an efficient alternative to full-weight adaptation in federated fine-tuning of language models, significantly reducing computational costs. By adjusting ranks for each client, federated LoRA enables…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-18 Yuji Byun , Jaeho Lee

Serving large language models (LLMs) is expensive, especially for providers hosting many models, making cost reduction essential. The unique workload patterns of serving multiple LLMs (i.e., multi-LLM serving) create new opportunities and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-14 Shan Yu , Jiarong Xing , Yifan Qiao , Mingyuan Ma , Yangmin Li , Yang Wang , Shuo Yang , Zhiqiang Xie , Shiyi Cao , Ke Bao , Ion Stoica , Harry Xu , Ying Sheng

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve…

Machine Learning · Computer Science 2025-05-21 Yifan Sui , Hao Wang , Hanfei Yu , Yitao Hu , Jianxun Li , Hao Wang

Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networks with minimal computational and memory overhead. Despite…

Machine Learning · Computer Science 2026-04-24 Bingcong Li , Yilang Zhang , Georgios B. Giannakis

We consider the problem of learning a mixture of Random Utility Models (RUMs). Despite the success of RUMs in various domains and the versatility of mixture RUMs to capture the heterogeneity in preferences, there has been only limited…

Machine Learning · Statistics 2020-04-01 Devavrat Shah , Dogyoon Song

GPU kernel optimization has long been a central challenge at the intersection of high-performance computing and machine learning. Efficient kernels are crucial for accelerating large language model (LLM) training and serving, yet attaining…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-04 Anjiang Wei , Tianran Sun , Yogesh Seenichamy , Hang Song , Anne Ouyang , Azalia Mirhoseini , Ke Wang , Alex Aiken

Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high cost of retraining. While parameter-efficient tuning methods…

Machine Learning · Computer Science 2026-02-06 Prakhar Kaushik , Ankit Vaidya , Shravan Chaudhari , Rama Chellappa , Alan Yuille

Deep Learning (DL) models have achieved superior performance. Meanwhile, computing hardware like NVIDIA GPUs also demonstrated strong computing scaling trends with 2x throughput and memory bandwidth for each generation. With such strong…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-05-26 Fuxun Yu , Di Wang , Longfei Shangguan , Minjia Zhang , Chenchen Liu , Xiang Chen

Fine-tuning is the primary methodology for tailoring pre-trained large language models to specific tasks. As the model's scale and the diversity of tasks expand, parameter-efficient fine-tuning methods are of paramount importance. One of…

Machine Learning · Computer Science 2024-01-10 Wenhan Xia , Chengwei Qin , Elad Hazan

Large Language Models have shown remarkable capabilities in the NLP domain. Their effectiveness can mainly be attributed to their ability to adapt to an array of downstream tasks. However, generally, full fine-tuning is a computationally…

Computation and Language · Computer Science 2025-06-10 Harsh Bihany , Shubham Patel , Ashutosh Modi

Vision Transformers (ViTs) have been widely adopted in vision tasks due to their strong transferability. In Federated Learning (FL), where full fine-tuning is communication heavy, Low-Rank Adaptation (LoRA) provides an efficient and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Zihao Peng , Nan Zou , Jiandian Zeng , Guo Li , Ke Chen , Boyuan Li , Tian Wang

Low-rank adaptation (LoRA) is one of the most popular task-specific parameter-efficient fine-tuning (PEFT) methods on pre-trained language models for its good performance and computational efficiency. LoRA injects a product of two trainable…

Machine Learning · Computer Science 2024-03-20 Youbang Sun , Zitao Li , Yaliang Li , Bolin Ding

Low-Rank Adaptation (LoRA) has emerged as a popular parameter-efficient fine-tuning (PEFT) method for Large Language Models (LLMs), yet it still incurs notable overhead and suffers from parameter interference in multi-task scenarios. We…

Machine Learning · Computer Science 2025-08-05 Juzheng Zhang , Jiacheng You , Ashwinee Panda , Tom Goldstein

We introduce a reformulation of regularized low-rank recovery models to take advantage of GPU, multiple CPU, and hybridized architectures. Low-rank recovery often involves nuclear-norm minimization through iterative thresholding of singular…

Optimization and Control · Mathematics 2017-10-05 Derek Driggs , Stephen Becker , Aleksandr Aravkin

Chart-to-code generation is a critical task in automated data visualization, translating complex chart structures into executable programs. While recent Multi-modal Large Language Models (MLLMs) improve chart representation, existing…

Software Engineering · Computer Science 2025-12-01 Yifei Wang , Jacky Keung , Zhenyu Mao , Jingyu Zhang , Yuchen Cao

Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational capacity often lags behind full fine-tuning. Within the context of LoRA, a key open question…

Machine Learning · Computer Science 2025-11-04 Xin Yu , Cong Xie , Ziyu Zhao , Tiantian Fan , Lingzhou Xue , Zhi Zhang

Parameter-efficient tuning (PEFT) techniques like low-rank adaptation (LoRA) offer training efficiency on Large Language Models, but their impact on model performance remains limited. Recent efforts integrate LoRA and Mixture-of-Experts…

Computation and Language · Computer Science 2024-02-14 Chongyang Gao , Kezhen Chen , Jinmeng Rao , Baochen Sun , Ruibo Liu , Daiyi Peng , Yawen Zhang , Xiaoyuan Guo , Jie Yang , VS Subrahmanian

Quantization followed by parameter-efficient fine-tuning has emerged as a promising paradigm for downstream adaptation under tight GPU memory constraints. However, this sequential pipeline fails to leverage the intricate interaction between…

Machine Learning · Computer Science 2026-02-27 Changhai Zhou , Shiyang Zhang , Yuhua Zhou , Qian Qiao , Jun Gao , Cheng Jin , Kaizhou Qin , Weizhong Zhang

Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. However, in multi-task learning (MTL) scenarios, LoRA tends to…

This study proposes a simple yet effective LoRA merge method to achieve LLM adaptation for low-resource language generation tasks. The LoRA merge technique, which integrates multiple LoRA modules trained on different tasks, has gained…

Computation and Language · Computer Science 2025-06-02 Ryota Miyano , Yuki Arase