Yuwen Hu
AI Frameworks Engineer at 英特尔
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolYuwen Hu is an AI Frameworks Engineer based in Shanghai with six years of experience building and documenting tooling for machine learning infrastructure. Currently at Intel, Yuwen focuses on making large language model inference and fine-tuning accessible across diverse Intel XPU hardware, and has contributed technical documentation and runnable Jupyter tutorials to the popular intel/ipex-llm project. With a strong academic foundation from Shanghai Jiao Tong University and KTH (plus coursework in Aachen), Yuwen blends systems-level understanding of hardware-accelerated ML with practical developer-facing communication. Past roles span web development and teaching assistance, reflecting an ability to switch between hands-on coding, educational outreach, and clear technical writing. Colleagues find Yuwen particularly effective at turning complex deployment nuances into crisp, reproducible docs and examples.
6 years of coding experience
KTH Royal Institute of TechnologyBachelor of Engineering - BE, Electrical and Computer Engineering, Bachelor of Engineering - BE, Electrical and Computer Engineering at 上海交通大学Computer Science, Computer Science at 德国亚琛工业大学
Github Skills (3)
jupyter-notebook10
sphinx10
documentation10
Programming languages (10)
Github contributions (5)
intel/ipex-llm
Jul 2022 - Jan 2023
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, 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, GraphRAG, DeepSpeed, Axolotl, etc
Role in this project:
Technical Writer
Technical WriterContributions:895 reviews, 44 commits, 909 PRs in 6 months
Contributions summary:Yuwen's commits primarily involved integrating and updating Jupyter Notebook files within the ReadtheDocs documentation for the `ipex-llm` repository. These updates included adding the `nbsphinx` extension, incorporating specific notebook files, and modifying existing notebooks by renaming titles, adding navigation texts, and removing outputs. The contributions focus on improving the documentation and making it accessible through ReadtheDocs.
llm-inferencellama2pythonfinetuningllama
intel-staging/llama_index
Mar 2024 - Jun 2024
LlamaIndex is a data framework for your LLM applications
Contributions:2 reviews, 23 PRs, 28 pushes in 2 months
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.