Ruonan Wang
AI Frameworks Engineer at Intel Corporation
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolRuonan Wang is an AI Frameworks Engineer at Intel in Shanghai with four years of experience building and documenting tooling for efficient on-device LLM inference. With a Master's in Intelligent Science and Technology from Beijing University of Posts and Telecommunications, she focuses on making large models run smoothly on Intel XPUs and hybrid setups. At Intel she has been a key technical writer and documentation maintainer for the popular ipex-llm project, producing how-to guides, examples, and UX-minded docs enhancements that help developers integrate LLMs with ecosystems like HuggingFace, LangChain and vLLM. Her work bridges engineering and developer experience—improving accessibility through content structure, internal linking and frontend touches like CSS for docs. Colleagues rely on her to translate low-level optimization details into clear, actionable guidance for practitioners deploying local inference and fine-tuning workflows.
4 years of coding experience
Master's degree, Intelligent science and technology, Master's degree, Intelligent science and technology at Beijing University of Posts and Telecommunications
Github Skills (7)
markdown10
markdown-it10
documentation10
technical-writing10
repos9
git-repository9
css9
Programming languages (6)
Github contributions (5)
intel/ipex-llm
Jun 2022 - Jan 2023
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.
Role in this project:
Technical Writer
Technical WriterContributions:1129 reviews, 139 commits, 815 PRs in 7 months
Contributions summary:Ruonan's contributions are centered on creating and maintaining documentation for the "ipex-llm" repository. They added how-to guides and examples, as well as updated the existing documentation, including the introduction of new topics and content organization within the project's documentation structure. This included the addition of CSS styling and internal linking, emphasizing a focus on user accessibility and clarity.
llm-inferencellama2pythonfinetuningllama
rnwang04/ipex-llm
Mar 2024 - Apr 2025
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max). A PyTorch LLM library that seamlessly integrates with HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, ModelScope, etc.
Contributions:5 PRs, 485 pushes, 207 branches in 1 year
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.