merrymercy
Training by day, inference by night.
Funding Links: https://github.com/sponsors/merrymercy
- Name: Lianmin Zheng
- Location: Bay Arena, CA
- Company: xAI
- Kind: user
- Followers: 3305
- Following: 160
- Total stars: 3023
- Repositories count: 53
- Created at: 2022-11-16T00:19:08.243Z
- Updated at: 2025-03-28T20:34:30.694Z
- Last synced at: 2025-03-28T20:34:30.693Z
GitHub Sponsors Profile
👋 Hey there! I'm Lianmin Zheng.
Open Source Projects
I am leading or co-leading the development of the following projects with a talented team and a passionate community of contributors.
SGLang: an efficient interface and runtime for interaction with LLMs.
FastChat: an open platform for training, serving, and evaluating large language model based chatbots. It powers our LMSYS projects such as Vicuna and Chatbot Arena.
Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality.
Chatbot Arena: benchmarking LLMs in the wild with Elo ratings.
Alpa: an auto-parallelizer for training and serving large-scale neural networks.
Besides, I am fortunate to have made significant contributions to the following projects.
TVM: an end-to-end deep learning compiler.
FlexGen: high-throughput generative inference of large language models with a single GPU.
About me
My interests are scalable and accelerated systems for machine learning. You can find me on:
My website
Google Scholar
Twitter
🎉 If you are using any of my open-source projects and would like to show your appreciation, you can sponsor me on this page to support the future development of these projects.
- Current Sponsors: 3
- Past Sponsors: 8
- Total Sponsors: 11
- Minimum Sponsorship: $1.00
Featured Works
sgl-project/sglang
SGLang is a fast serving framework for large language models and vision language models.
Language: Python - Stars: 12695lm-sys/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Language: Python - Stars: 38248FMInference/FlexLLMGen
Running large language models on a single GPU for throughput-oriented scenarios.
Language: Python - Stars: 9290alpa-projects/alpa
Training and serving large-scale neural networks with auto parallelization.
Language: Python - Stars: 3121Active Sponsors
Past Sponsors
Sponsor Breakdown
- User: 9
- Organization: 1