English | 繁體

Search in the results

UM

Browse/Search Results:  1-2 of 2 Help

Selected(0)Clear Items/Page:    Sort:
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  
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