Lianmin Zheng

发表

TVM: An Automated End-to-End Optimizing Compiler for Deep Learning

Haichen Shen, Thierry Moreau, Meghan Cowan, 2018, OSDI.

Learning to Optimize Tensor Programs

Thierry Moreau, Luis Ceze, Tianqi Chen, 2018, NeurIPS.

DEEPWAVE: Deep Learning based Real-time Water Wave Simulation

Lianmin Zheng, Jinning Li, 2018 .

GACT: Activation Compressed Training for General Architectures

Lianmin Zheng, Dequan Wang, M. Mahoney, 2022, ArXiv.

Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning

Joseph Gonzalez, I. Stoica, Lianmin Zheng, 2022, OSDI.

This paper is included in the Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation.

E. Xing, H. Zhang, Lianmin Zheng, 2022 .

TensorIR: An Abstraction for Automatic Tensorized Program Optimization

Cody Hao Yu, Tianqi Chen, Lianmin Zheng, 2022, ASPLOS.

GACT: Activation Compressed Training for Generic Network Architectures

Michael W. Mahoney, Zhiyuan Liu, Lianmin Zheng, 2022, ICML.

GACT: Activation Compressed Training for General Architectures

Michael W. Mahoney, Lianmin Zheng, Dequan Wang, 2022, ArXiv.

On Optimizing the Communication of Model Parallelism

Eric P. Xing, Qirong Ho, Joseph E. Gonzalez, 2022, ArXiv.

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training pdf

Ion Stoica, Joseph E. Gonzalez, Michael W. Mahoney, 2021, ICML.

Ansor : Generating High-Performance Tensor Programs for Deep Learning

Cody Hao Yu, Jun Yang, Koushik Sen, 2020, OSDI.

TVM: An Automated End-to-End Optimizing Compiler for Deep Learning pdf

Haichen Shen, Thierry Moreau, Luis Ceze, 2018 .

High-throughput Generative Inference of Large Language Models with a Single GPU

Daniel Y. Fu, Percy Liang, Christopher Ré, 2023, ArXiv.

Size-to-depth: A New Perspective for Single Image Depth Estimation pdf

Yiran Wu, Lianmin Zheng, Sihao Ying, 2018, ArXiv.

MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence pdf

Weinan Zhang, Jun Wang, Han Cai, 2017, AAAI.

Simple and Automatic Distributed Machine Learning on Ray

Ion Stoica, Lianmin Zheng, Hao Zhang, 2021, KDD.

Judging LLM-as-a-judge with MT-Bench and Chatbot Arena

Joseph E. Gonzalez, E. Xing, Lianmin Zheng, 2023, 2306.05685.

High-throughput Generative Inference of Large Language Models with a Single GPU

Daniel Y. Fu, Percy Liang, Christopher Ré, 2023, ICML.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Christopher Ré, Lianmin Zheng, Zhangyang Wang, 2023, 2306.14048.

A Hardware–Software Blueprint for Flexible Deep Learning Specialization

Thierry Moreau, Luis Ceze, Arvind Krishnamurthy, 2018, IEEE Micro.

Judging LLM-as-a-judge with MT-Bench and Chatbot Arena

E. Xing, Joseph Gonzalez, Lianmin Zheng, 2023, ArXiv.

TenSet: A Large-scale Program Performance Dataset for Learned Tensor Compilers

Tianqi Chen, I. Stoica, Lianmin Zheng, 2021, NeurIPS Datasets and Benchmarks.

On Optimal Caching and Model Multiplexing for Large Model Inference

Michael I. Jordan, Lianmin Zheng, Banghua Zhu, 2023, arXiv.org.

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Christopher Ré, Lianmin Zheng, Yuandong Tian, 2023, NeurIPS.

NumS: Scalable Array Programming for the Cloud

I. Stoica, Alvin Cheung, Lianmin Zheng, 2022, ArXiv.

Efficient Memory Management for Large Language Model Serving with PagedAttention

Joseph E. Gonzalez, Lianmin Zheng, Zhuohan Li, 2023, SOSP.

Rethinking Benchmark and Contamination for Language Models with Rephrased Samples

Lianmin Zheng, Wei-Lin Chiang, I. Stoica, 2023, ArXiv.

Judging LLM-as-a-judge with MT-Bench and Chatbot Arena

E. Xing, Joseph Gonzalez, Lianmin Zheng, 2023, NeurIPS.

Ansor : Generating High-Performance Tensor Programs for Deep Learning

Cody Hao Yu, I. Stoica, Joseph E. Gonzalez, 2020, OSDI.

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Lianmin Zheng, I. Stoica, Coleman Hooper, 2023, ArXiv.

This paper is included in the Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation

Z. Chen, Joseph E. Gonzalez, Lianmin Zheng, 2022 .

SGLang: Efficient Execution of Structured Language Model Programs

Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, 2023, 2312.07104.

HuatuoGPT, Towards Taming Language Models To Be a Doctor

Collin Burns, Azalia Mirhoseini, Anna Goldie, 2022 .

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Lianmin Zheng, Coleman Hooper, Ying Sheng, 2023, ArXiv.

Simple and Automatic Distributed Machine Learning on Ray

Lianmin Zheng, Hao Zhang, Zhuohan Li, 2021, KDD.

On Optimal Caching and Model Multiplexing for Large Model Inference

Michael I. Jordan, Lianmin Zheng, Banghua Zhu, 2023, ArXiv.