MLSys

Publications

2024

Alok Tripathy, Katherine A. Yelick, Aydin Buluç
Distributed Matrix-Based Sampling for Graph Neural Network Training. MLSys (2024)
Size Zheng, Renze Chen, Meng Li, Zihao Ye, Luis Ceze, Yun Liang
vMCU: Coordinated Memory Management and Kernel Optimization for DNN Inference on MCUs. MLSys (2024)
Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, Alexey Tumanov
VIDUR: A Large-Scale Simulation Framework for LLM Inference. MLSys (2024)
Haihao Shen, Naveen Mellempudi, Xin He, Qun Gao, Chang Wang, Mengni Wang
Efficient Post-training Quantization with FP8 Formats. MLSys (2024)
Muhammad Adnan, Akhil Arunkumar, Gaurav Jain, Prashant J. Nair, Ilya Soloveychik, Purushotham Kamath
Keyformer: KV Cache reduction through key tokens selection for Efficient Generative Inference. MLSys (2024)
Yash Akhauri, Mohamed S. Abdelfattah
On Latency Predictors for Neural Architecture Search. MLSys (2024)
Song Bian, Dacheng Li, Hongyi Wang, Eric P. Xing, Shivaram Venkataraman
Does Compressing Activations Help Model Parallel Training? MLSys (2024)
Isha Chaudhary, Alex Renda, Charith Mendis, Gagandeep Singh
COMET: Neural Cost Model Explanation Framework. MLSys (2024)
Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han
AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. MLSys (2024)
Yifei Xu, Yuning Chen, Xumiao Zhang, Xianshang Lin, Pan Hu, Yunfei Ma, Songwu Lu, Wan Du, Zhuoqing Mao, Ennan Zhai, Dennis Cai
CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation. MLSys (2024)
Jingtian Dang, Jianming Tong, Anupam Golder, Cong Hao, Arijit Raychowdhury, Tushar Krishna
Accurate Low-Degree Polynomial Approximation of Non-Polynomial Operators for Fast Private Inference in Homomorphic Encryption. MLSys (2024)
Lequn Chen, Zihao Ye, Yongji Wu, Danyang Zhuo, Luis Ceze, Arvind Krishnamurthy
Punica: Multi-Tenant LoRA Serving. MLSys (2024)
Milos Nikolic, Enrique Torres-Sánchez, Jiahui Wang, Ali Hadi Zadeh, Mostafa Mahmoud, Ameer Abdelhadi, Kareem Ibrahim, Andreas Moshovos
Schrodinger's FP Training Neural Networks with Dynamic Floating-Point Containers. MLSys (2024)
Yuxuan Zhu, Jiachen Liu, Mosharaf Chowdhury, Fan Lai
FedTrans: Efficient Federated Learning via Multi-Model Transformation. MLSys (2024)
In Gim, Guojun Chen, Seung-Seob Lee, Nikhil Sarda, Anurag Khandelwal, Lin Zhong
Prompt Cache: Modular Attention Reuse for Low-Latency Inference. MLSys (2024)
Zhenyu Zhang, Shiwei Liu, Runjin Chen, Bhavya Kailkhura, Beidi Chen, Atlas Wang
Q-Hitter: A Better Token Oracle for Efficient LLM Inference via Sparse-Quantized KV Cache. MLSys (2024)
Yunhao Yang, Neel P. Bhatt, Tyler Ingebrand, William Ward, Steven Carr, Atlas Wang, Ufuk Topcu
Fine-Tuning Language Models Using Formal Methods Feedback: A Use Case in Autonomous Systems. MLSys (2024)
Ke Hong, Guohao Dai, Jiaming Xu, Qiuli Mao, Xiuhong Li, Jun Liu, Kangdi Chen, Yuhan Dong, Yu Wang
FlashDecoding++: Faster Large Language Model Inference with Asynchronization, Flat GEMM Optimization, and Heuristics. MLSys (2024)
Shixiong Qi, K. K. Ramakrishnan, Myungjin Lee
LIFL: A Lightweight, Event-driven Serverless Platform for Federated Learning. MLSys (2024)
Chenyu Jiang, Ye Tian, Zhen Jia, Shuai Zheng, Chuan Wu, Yida Wang
Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping. MLSys (2024)
Gyudong Kim, Mehdi Ghasemi, Soroush Heidari, Seungryong Kim, Young Geun Kim, Sarma B. K. Vrudhula, Carole-Jean Wu
HeteroSwitch: Characterizing and Taming System-Induced Data Heterogeneity in Federated Learning. MLSys (2024)
Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry
ACROBAT: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time. MLSys (2024)
Elias Frantar, Dan Alistarh
QMoE: Sub-1-Bit Compression of Trillion Parameter Models. MLSys (2024)
Proceedings of the Seventh Annual Conference on Machine Learning and Systems, MLSys 2024, Santa Clara, CA, USA, May 13-16, 2024 MLSys (2024)
Liang Luo, Buyun Zhang, Michael Tsang, Yinbin Ma, Ching-Hsiang Chu, Yuxin Chen, Shen Li, Yuchen Hao, Yanli Zhao, Guna Lakshminarayanan, Ellie Wen, Jongsoo Park, Dheevatsa Mudigere, Maxim Naumov
Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large Scale Recommendation. MLSys (2024)
Yichen Qian, Yongyi He, Rong Zhu, Jintao Huang, Zhijian Ma, Haibin Wang, Yaohua Wang, Xiuyu Sun, Defu Lian, Bolin Ding, Jingren Zhou
UniDM: A Unified Framework for Data Manipulation with Large Language Models. MLSys (2024)
Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Chen Wang, Hubertus Franke, Zbigniew Kalbarczyk, Tamer Basar, Ravi K. Iyer
FLASH: Fast Model Adaptation in ML-Centric Cloud Platforms. MLSys (2024)
Jian Meng, Yuan Liao, Anupreetham Anupreetham, Ahmed Hassan, Shixing Yu, Han-Sok Suh, Xiaofeng Hu, Jae-sun Seo
Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design. MLSys (2024)
Yubo Gao, Maryam Haghifam, Christina Giannoula, Renbo Tu, Gennady Pekhimenko, Nandita Vijaykumar
Proteus: Preserving Model Confidentiality during Graph Optimizations. MLSys (2024)
Shan Yu, Zhenting Zhu, Yu Chen, Hanchen Xu, Pengzhan Zhao, Yang Wang, Arthi Padmanabhan, Hugo Latapie, Harry Xu
VQPy: An Object-Oriented Approach to Modern Video Analytics. MLSys (2024)
Zhixu Du, Shiyu Li, Yuhao Wu, Xiangyu Jiang, Jingwei Sun, Qilin Zheng, Yongkai Wu, Ang Li, Hai Li, Yiran Chen
SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models. MLSys (2024)
Ilia Markov, Kaveh Alim, Elias Frantar, Dan Alistarh
L-GreCo: Layerwise-adaptive Gradient Compression For Efficient Data-parallel Deep Learning. MLSys (2024)
Yilong Zhao, Chien-Yu Lin, Kan Zhu, Zihao Ye, Lequn Chen, Size Zheng, Luis Ceze, Arvind Krishnamurthy, Tianqi Chen, Baris Kasikci
Atom: Low-Bit Quantization for Efficient and Accurate LLM Serving. MLSys (2024)
Ye Tian, Zhen Jia, Ziyue Luo, Yida Wang, Chuan Wu
DiffusionPipe: Training Large Diffusion Models with Efficient Pipelines. MLSys (2024)
Mohamed Assem Ibrahim, Shaizeen Aga, Ada Li, Suchita Pati, Mahzabeen Islam
JIT-Q: Just-in-time Quantization with Processing-In-Memory for Efficient ML Training. MLSys (2024)
Ying Sheng, Shiyi Cao, Dacheng Li, Coleman Hooper, Nicholas Lee, Shuo Yang, Christopher Chou, Banghua Zhu, Lianmin Zheng, Kurt Keutzer, Joseph Gonzalez, Ion Stoica
SLoRA: Scalable Serving of Thousands of LoRA Adapters. MLSys (2024)
Xuanlei Zhao, Bin Jia, Haotian Zhou, Ziming Liu, Shenggan Cheng, Yang You
HeteGen: Efficient Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices. MLSys (2024)
Kiwan Maeng, G. Edward Suh
Accelerating ReLU for MPC-Based Private Inference with a Communication-Efficient Sign Estimation. MLSys (2024)

2023