Lianmin Zheng
Co-founder of LMSYS Org and core author of vLLM, SGLang, Vicuna, FastChat, and Chatbot Arena; PhD candidate at UC Berkeley.
- Role
- grad-student
- Currently at
- University of California, Berkeley
- twitter.com/lm_zheng
- GitHub
- github.com/merrymercy
- Scholar
- scholar.google.com/citations
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
ICML
Post-Training Sparse Attention with Double Sparsity
arXiv 2024
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
NeurIPS
Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90% ChatGPT Quality
blog
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
arXiv 2023
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
arXiv 2023
Efficient Memory Management for Large Language Model Serving with PagedAttention
arXiv 2023
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
arXiv 2023
Rethinking Benchmark and Contamination for Language Models with Rephrased Samples
arXiv 2023
SGLang: Efficient Execution of Structured Language Model Programs
arXiv 2023
On Optimal Caching and Model Multiplexing for Large Model Inference
arXiv 2023
GACT: Activation Compressed Training for Generic Network Architectures
arXiv 2022
Affiliations
Frequent co-authors
10from 12 papers
Ying Sheng
researcher
Ion Stoica
professor / co-founder
Joseph E. Gonzalez
Clark Barrett
Hao Zhang
professor
Wei-Lin Chiang
co-founder / President
Zhuohan Li
researcher
Banghua Zhu
professor
Dacheng Li
grad-student
Joseph E. Gonzalez
professor