Lianmin Zheng
VERIFIED TECHNICAL DOSSIERSources checked

Lianmin Zheng

Co-Founder & AI Systems Researcher

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Lianmin Zheng. Every entry undergoes editorial source verification.

#1
IMPLEMENTATION Checked 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.

Model & Execution Context:DeepSeek-V3/R1, LLaMA-3, Qwen-2.5; FlashInfer integration; Triton custom kernels.
Scope & Limitations

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

#2
RESEARCH Checked 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.

Model & Execution Context:Crowdsourced human Elo ratings across 1M+ pairwise conversations and GPT-4 automated judgment.
Scope & Limitations

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