On AI Lounge since Nov 2026
Linzhang Chen
Member #3,986DeveloperL2ai project manager, independent
Striving to make LLM inference more efficient.
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×2Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 2 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×2Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
Linzhang Chen hasn't posted yet.
Pinned projects
Reproducible llama.cpp CPU inference profiling and a deterministic LLM serving simulator with continuous batching, KV cache, prefix caching, and workload-driven latency analysis.
continuous-batchingkv-cachellama-cppllm-inferencellm-serving
Evidence-backed structural validation of Kimi K3 UD-IQ1_M and UD-Q4_K_XL split GGUF releases using OMIV.
ai-infrastructureggufkimi-k3llama-cppllm
A production-oriented LLM engineering platform with OpenAI-compatible serving, streaming, observability, evaluation, reproducible experiments, and deterministic RAG.
ai-infrastructure
dockerevaluationexperiment-tracking
fastapi
Offline-first evidence and verification framework for AI model artifacts, transformations, runtime identity, and provenance.
ai-supply-chainartifact-verificationggufllmmlops
Evidence-grounded AI agent prototype for regulated financial workflows with AWS, Docker, Databricks, evaluation and human-in-the-loop governance.
About
Linzhang Chen is an independent AI project manager in Tokyo who also works as a developer on large language model tooling. Public GitHub work under the handle 200lz includes a reproducible profiler for llama.cpp CPU inference and a deterministic simulator of LLM serving with continuous batching and prefix caching. Linzhang's current focus is improving the efficiency with which large language models run at inference time.
