MLSys 2025 Conference Submissions

TurboAttention: Efficient attention approximation for high throughputs llm
Hao Kang, Srikant Bharadwaj, James Hensman, Tushar Krishna, Victor Rühle, Saravan Rajmohan
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025 withshepherding
- Readers: Everyone
Supply-Chain Attacks in Machine Learning Frameworks
Yue Gao, Ilia Shumailov, Kassem Fawaz
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
ScaleFusion: Scalable Inference of Spatial-Temporal Diffusion Transformers for High-Resolution Long Video Generation
Jiacheng Yang, Jun Wu, Zhen Zhang, Xinwei Fu, Zhiying Xu, Zhen Jia, Yida Wang, Gennady Pekhimenko
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation
Zhiyu Mei, Wei Fu, Kaiwei Li, Guangju Wang, Huanchen Zhang, Yi Wu
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025 withshepherding
- Readers: Everyone
DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling
Sohaib Ahmad, Qizheng Yang, Haoliang Wang, Ramesh K. Sitaraman, Hui Guan
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
A Bring-Your-Own-Model Approach for ML-Driven Storage Placement in Warehouse-Scale Computers
Chenxi Yang, Yan Li, Martin Maas, Mustafa Uysal, Ubaid Ullah Hafeez, Arif Merchant, Richard McDougall
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training
Daiyaan Arfeen, Zhen Zhang, Xinwei Fu, Gregory Ganger, Yida Wang
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators
Beichen Huang, Yueming Yuan, ZELEI SHAO, Minjia Zhang
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs
Zichao Yue, Chenhui Deng, Zhiru Zhang
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training
Mingyu Liang, Hiwot Tadese Kassa, Wenyin Fu, Brian Coutinho, Louis Feng, Christina Delimitrou
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
Know Where You’re Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
Neel P. Bhatt, Yunhao Yang, Rohan Siva, Daniel Milan, ufuk topcu, Zhangyang Wang
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
FlexInfer: Flexible LLM Inference with CPU Computations
Seonjin Na, Geonhwa Jeong, Byung Hoon Ahn, Aaron Jezghani, Jeffrey Young, Christopher J. Hughes, Tushar Krishna, Hyesoon Kim
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
Efficient On-Device Machine Learning with a Biologically-Plausible Forward-Only Algorithm
Baichuan Huang, Amir Aminifar
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
Seesaw: High-throughput LLM Inference via Model Re-sharding
Qidong Su, Wei Zhao, Xin Li, Muralidhar Andoorveedu, Chenhao Jiang, Zhanda Zhu, Kevin Song, Christina Giannoula, Gennady Pekhimenko
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learning
Minxue Tang, Yitu Wang, Jingyang Zhang, Louis DiValentin, Aolin Ding, Amin Hass, Yiran Chen, Hai Li
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
QServe:W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
Yujun Lin, Haotian Tang, Shang Yang, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, Song Han
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Shang Yang, Junxian Guo, Haotian Tang, Qinghao Hu, Guangxuan Xiao, Jiaming Tang, Yujun Lin, Zhijian Liu, Yao Lu, Song Han
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds
Yinfang Chen, Manish Shetty, Gagan Somashekar, Minghua Ma, Yogesh Simmhan, Jonathan Mace, Chetan Bansal, Rujia Wang, Saravan Rajmohan
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
FastTree: Optimizing Attention Kernel and Runtime for Tree-Structured LLM Inference
Zaifeng Pan, Yitong Ding, Yue Guan, Zheng Wang, Zhongkai Yu, Xulong Tang, Yida Wang, Yufei Ding
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
Interference-aware Edge Runtime Prediction with Conformal Matrix Completion
Tianshu Huang, Arjun Ramesh, Emily Ruppel, Nuno Pereira, Anthony Rowe, Carlee Joe-Wong
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution
Zhiqiang Xie, Hao Kang, Ying Sheng, Tushar Krishna, Kayvon Fatahalian, Christos Kozyrakis
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025 withshepherding
- Readers: Everyone
On Distributed Larger-Than-Memory Subset Selection With Pairwise Submodular Functions
Maximilian Böther, Abraham Sebastian, Pranjal Awasthi, Ana Klimovic, Srikumar Ramalingam
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
The Hidden Bloat in Machine Learning Systems
Huaifeng Zhang, Ahmed Ali-Eldin
- Published: 11 Feb 2025, Last Modified: 16 May 2025
- MLSys 2025
- Readers: Everyone
COMET: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
Shulai Zhang, Ningxin Zheng, Haibin Lin, Ziheng Jiang, Wenlei Bao, Chengquan Jiang, Qi Hou, Weihao Cui, Size Zheng, Li-Wen Chang, Quan Chen, Xin Liu
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone
APOLLO: SGD-like Memory, AdamW-level Performance
Hanqing Zhu, Zhenyu Zhang, Wenyan Cong, Xi Liu, Sem Park, Vikas Chandra, Bo Long, David Z. Pan, Zhangyang Wang, Jinwon Lee
- Published: 11 Feb 2025, Last Modified: 13 May 2025
- MLSys 2025
- Readers: Everyone