English | 繁體

Search in the results

UM

Browse/Search Results:  1-10 of 19 Help

Selected(0)Clear Items/Page:    Sort:
面向云服务的性能与隔离性定制化硬件资源抽象方法 Patent
专利类型: 发明专利Invention,
Authors:  YE KEJIANG;  SU LINYU;  LIN YANYING;  XU CHENGZHONG
Favorite |  | Submit date：2022/08/29
Cloud Services  Hardware Resource Abstraction  Fpga  
多维资源混部干扰模型驱动的调度策略 Patent
专利类型: 发明专利Invention,
Authors:  YE KEJIANG;  LIN PENG;  XU CHENGZHONG
Favorite |  | Submit date：2022/08/29
Colocation  Scheduling Strategy  Interference Model  
基于无服务器计算的高并发低时延云服务支撑方法 Patent
专利类型: 发明专利Invention,
Authors:  YE KEJIANG;  LIN YANYING;  XU CHENGZHONG
Favorite |  | Submit date：2022/08/26
Serverless  Low Latency  High Throughput  
QUART: Latency-Aware FaaS System for Pipelining Large Model Inference Conference paper
Lin, Yanying, Li, Yanbo, Peng, Shijie, Tang, Yingfei, Luo, Shutian, Shen, Haiying, Xu, Chengzhong, Ye, Kejiang. QUART: Latency-Aware FaaS System for Pipelining Large Model Inference[C]:Institute of Electrical and Electronics Engineers Inc., 2024.
Authors:  Lin, Yanying;  Li, Yanbo;  Peng, Shijie;  Tang, Yingfei;  Luo, Shutian; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0 | Submit date：2024/10/10
Processor Scheduling  Computational Modeling  Tail  Position Measurement  Resource Management  Low Latency Communication  Distributed Computing  Pipeline Inference  Large Model  Serverless  Latency Aware  
Derm: SLA-aware Resource Management for Highly Dynamic Microservices Conference paper
Chen Liao, Shutian Luo, Chenyu Lin, Zizhao Mo, XU HUANLE, Kejiang Ye, Chengzhong Xu. Derm: SLA-aware Resource Management for Highly Dynamic Microservices[C]:Institute of Electrical and Electronics Engineers Inc., 2024, 424 - 436.
Authors:  Chen Liao;  Shutian Luo;  Chenyu Lin;  Zizhao Mo;  XU HUANLE; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0 | Submit date：2024/08/23
Dynamic Microservice Graph  Resource Scaling  Uncertainty  
EINS: Edge-Cloud Deep Model Inference with Network-Efficiency Schedule in Serverless Conference paper
Peng, Shijie, Lin, Yanying, Chen, Wenyan, Tang, Yingfei, Duan, Xu, Ye, Kejiang. EINS: Edge-Cloud Deep Model Inference with Network-Efficiency Schedule in Serverless[C]:Institute of Electrical and Electronics Engineers Inc., 2024, 1376-1381.
Authors:  Peng, Shijie;  Lin, Yanying;  Chen, Wenyan;  Tang, Yingfei;  Duan, Xu; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0 | Submit date：2024/08/05
Edge-cloud Collaborative  Network-efficiency  Serverless Inference  
Optimizing Resource Management for Shared Microservices: A Scalable System Design Journal article
Luo, Shutian, Lin, Chenyu, Ye, Kejiang, Xu, Guoyao, Zhang, Liping, Yang, Guodong, Xu, Huanle, Xu, Chengzhong. Optimizing Resource Management for Shared Microservices: A Scalable System Design[J]. ACM Transactions on Computer Systems, 2024, 42(1-2).
Authors:  Luo, Shutian;  Lin, Chenyu;  Ye, Kejiang;  Xu, Guoyao;  Zhang, Liping; et al.
Favorite | TC[WOS]:3 TC[Scopus]:5  IF:2.0/2.6 | Submit date：2024/06/05
Additional Key Words And Phrasesshared Microservices  Resource Management  Sla Guarantees  
Planck: Optimizing LLM Inference Performance in Pipeline Parallelism with Fine-Grained SLO Constraint Conference paper
Lin, Yanying, Peng, Shijie, Wu, Shuaipeng, Li, Yanbo, Lu, Chengzhi, Xu, Chengzhong, Ye, Kejiang. Planck: Optimizing LLM Inference Performance in Pipeline Parallelism with Fine-Grained SLO Constraint[C]:Institute of Electrical and Electronics Engineers Inc., 2024, 1306-1313.
Authors:  Lin, Yanying;  Peng, Shijie;  Wu, Shuaipeng;  Li, Yanbo;  Lu, Chengzhi; et al.
Favorite | TC[WOS]:0 TC[Scopus]:1 | Submit date：2024/12/05
Llm Serving  Pipeline Bubble  Pipeline Parallelism  Slo Constraint  
Planck: Optimizing LLM Inference Performance in Pipeline Parallelism with Fine-Grained SLO Constraint Journal article
Lin, Yanying, Peng, Shijie, Wu, Shuaipeng, Li, Yanbo, Lu, Chengzhi, Xu, Chengzhong, Ye, Kejiang. Planck: Optimizing LLM Inference Performance in Pipeline Parallelism with Fine-Grained SLO Constraint[J]. Proceedings of the IEEE International Conference on Web Services, ICWS, 2024, 1306-1313.
Authors:  Lin, Yanying;  Peng, Shijie;  Wu, Shuaipeng;  Li, Yanbo;  Lu, Chengzhi; et al.
Favorite | TC[WOS]:0 TC[Scopus]:1 | Submit date：2024/12/26
LLM Serving  Pipeline Bubble  Pipeline Parallelism  SLO Constraint  
GcForest-based compound-protein interaction prediction model and its application in discovering small-molecule drugs targeting CD47 Journal article
Shan, Wenying, Chen, Lvqi, Xu, Hao, Zhong, Qinghao, Xu, Yinqiu, Yao, Hequan, Lin, Kejiang, Li, Xuanyi. GcForest-based compound-protein interaction prediction model and its application in discovering small-molecule drugs targeting CD47[J]. Frontiers in Chemistry, 2023, 11.
Authors:  Shan, Wenying;  Chen, Lvqi;  Xu, Hao;  Zhong, Qinghao;  Xu, Yinqiu; et al.
Favorite | TC[WOS]:3 TC[Scopus]:2  IF:3.8/4.8 | Submit date：2024/02/22
Artificial Intelligence  Compound-protein Interaction Prediction  Gcforest  Small-molecule Cd47 Inhibitors  Word2vec