Lianmin Zheng

Co-Founder & AI Systems Researcher

Sources checked
ABOUT

Co-founder of LMSYS Org, PhD researcher at UC Berkeley SkyLab, and creator of SGLang, FastChat, Vicuna, and Chatbot Arena. Pioneered RadixAttention and KV cache reuse runtime optimizations that power state-of-the-art inference engines across the open-weights ecosystem.

Areas of focus

Professional niches

THE WORK BEHIND THE PROFILE

Proof of Work

implementationChecked Sep 22, 2026

SGLang: Fast Serving Framework for Complex Language Model Programs

Engineered SGLang featuring RadixAttention, which maintains a radix tree over KV caches to enable automatic multi-turn and prefix cache reuse, delivering up to 5x higher throughput for complex multi-call LLM workflows.

Scope & limitations

Radix tree traversal introduces slight metadata lookup overhead for workloads with completely random, unshared prefixes.

Context: DeepSeek-V3/R1, LLaMA-3, Qwen-2.5; FlashInfer integration; Triton custom kernels.

View mission
researchChecked Sep 22, 2026

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

Co-authored the landmark NeurIPS 2023 paper establishing crowd-sourced, blind pairwise human evaluation (Chatbot Arena) and LLM-as-a-judge benchmarks, standardizing empirical foundation model comparison globally.

Scope & limitations

Susceptible to verbosity and style bias when using automated LLM evaluators without strict length-penalized rubrics.

Context: Crowdsourced human Elo ratings across 1M+ pairwise conversations and GPT-4 automated judgment.

View mission

Guides to evaluating AI expertise