SysML@Princeton

Research

A collection of the papers we have published.

Highlighted

citation image
[no title info]
[no publisher info]  ·  [no date info]  ·  [no id info]

All

2024

Marconi: Prefix Caching for the Era of Hybrid LLMs
Marconi: Prefix Caching for the Era of Hybrid LLMs
Rui Pan, Zhuang Wang, Zhen Jia, Can Karakus, Luca Zancato, Tri Dao, Yida Wang, Ravi Netravali
arXiv  ·  05 Dec 2024  ·  arxiv:2411.19379
large-language-models efficient-inference mamba-hybrid-models prefix-caching
Improving DNN Inference Throughput Using Practical, Per-Input Compute Adaptation
Improving DNN Inference Throughput Using Practical, Per-Input Compute Adaptation
Anand Padmanabha Iyer, Mingyu Guan, Yinwei Dai, Rui Pan, Swapnil Gandhi, Ravi Netravali
Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles  ·  04 Nov 2024  ·  doi:10.1145/3694715.3695978
large-language-models efficient-inference
Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving
Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving
Yinwei Dai, Rui Pan, Anand Iyer, Kai Li, Ravi Netravali
Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles  ·  04 Nov 2024  ·  doi:10.1145/3694715.3695963
GitHub
large-language-models efficient-inference

2023

Auxo
Auxo
Jiachen Liu, Fan Lai, Yinwei Dai, Aditya Akella, Harsha V. Madhyastha, Mosharaf Chowdhury
Proceedings of the 2023 ACM Symposium on Cloud Computing  ·  30 Oct 2023  ·  doi:10.1145/3620678.3624651
SIGIR 2023 Workshop on Retrieval Enhanced Machine Learning REML SIGIR 2023
SIGIR 2023 Workshop on Retrieval Enhanced Machine Learning (REML @ SIGIR 2023)
Michael Bendersky, Danqi Chen, Fernando Diaz, Hamed Zamani
Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval  ·  18 Jul 2023  ·  doi:10.1145/3539618.3591925
A Dataset Auditing Method for Collaboratively Trained Machine Learning Models
A Dataset Auditing Method for Collaboratively Trained Machine Learning Models
Yangsibo Huang, Chun-Yin Huang, Xiaoxiao Li, Kai Li
IEEE Transactions on Medical Imaging  ·  01 Jul 2023  ·  doi:10.1109/TMI.2022.3220706
Prefetching Using Principles of Hippocampal-Neocortical Interaction
Prefetching Using Principles of Hippocampal-Neocortical Interaction
Michael Wu, Ketaki Joshi, Andrew Sheinberg, Guilherme Cox, Anurag Khandelwal, Raghavendra Pradyumna Pothukuchi, Abhishek Bhattacharjee
Proceedings of the 19th Workshop on Hot Topics in Operating Systems  ·  22 Jun 2023  ·  doi:10.1145/3593856.3595901
Proceedings of the 20th USENIX Symposium on Networked System Design and Implementation NSDI 23 : April 17-19, 2023, Boston, MA, USA
Proceedings of the 20th USENIX Symposium on Networked System Design and Implementation (NSDI '23): April 17-19, 2023, Boston, MA, USA
USENIX Association  ·  01 Jan 2023  ·  isbn:978-1-939133-33-5

2022

Efficient flow scheduling in distributed deep learning training with echelon formation
Efficient flow scheduling in distributed deep learning training with echelon formation
Rui Pan, Yiming Lei, Jialong Li, Zhiqiang Xie, Binhang Yuan, Yiting Xia
Proceedings of the 21st ACM Workshop on Hot Topics in Networks  ·  14 Nov 2022  ·  doi:10.1145/3563766.3564096