Výsledky vyhledávání

Report

Ensuring Fair LLM Serving Amid Diverse Applications

Autor: Khan, Redwan Ibne Seraj, Jain, Kunal, Shen, Haiying, Mallick, Ankur, Parayil, Anjaly, Kulkarni, Anoop, Kofsky, Steve, Choudhary, Pankhuri, Amant, Renèe St., Wang, Rujia, Cheng, Yue, Butt, Ali R., Rühle, Victor, Bansal, Chetan, Rajmohan, Saravan

In a multi-tenant large language model (LLM) serving platform hosting diverse applications, some users may submit an excessive number of requests, causing the service to become unavailable to other users and creating unfairness. Existing fairness app

Externí odkaz: http://arxiv.org/abs/2411.15997

Zobrazit plný text záznamu

Report

Towards Persistent Memory based Stateful Serverless Computing for Big Data Applications

Autor: Li, Yuze, Assogba, Kevin, Tripathy, Abhijit, Arif, Moiz, Rafique, M. Mustafa, Butt, Ali R., Nikolopoulos, Dimitrios

The Function-as-a-service (FaaS) computing model has recently seen significant growth especially for highly scalable, event-driven applications. The easy-to-deploy and cost-efficient fine-grained billing of FaaS is highly attractive to big data appli

Externí odkaz: http://arxiv.org/abs/2309.01662

Zobrazit plný text záznamu

Report

IP-FL: Incentivized and Personalized Federated Learning

Autor: Khan, Ahmad Faraz, Wang, Xinran, Le, Qi, Abdeen, Zain ul, Khan, Azal Ahmad, Ali, Haider, Jin, Ming, Ding, Jie, Butt, Ali R., Anwar, Ali

Existing incentive solutions for traditional Federated Learning (FL) focus on individual contributions to a single global objective, neglecting the nuances of clustered personalization with multiple cluster-level models and the non-monetary incentive

Externí odkaz: http://arxiv.org/abs/2304.07514

Zobrazit plný text záznamu

Report

Towards cost-effective and resource-aware aggregation at Edge for Federated Learning

Autor: Khan, Ahmad Faraz, Li, Yuze, Wang, Xinran, Haroon, Sabaat, Ali, Haider, Cheng, Yue, Butt, Ali R., Anwar, Ali

Federated Learning (FL) is a machine learning approach that addresses privacy and data transfer costs by computing data at the source. It's particularly popular for Edge and IoT applications where the aggregator server of FL is in resource-capped edg

Externí odkaz: http://arxiv.org/abs/2204.07767

Zobrazit plný text záznamu