Guancheng Fu
AI Framework Engineer at 英特尔亚太研发有限公司
Shandong, China
Summary
🤩
Rockstar🎓
Top SchoolGuancheng Fu is an AI Framework Engineer with three years of hands-on experience building and deploying LLM serving infrastructure at Intel APAC while pursuing a Master’s in Software Engineering at Duke. He focuses on back-end and DevOps work to accelerate local LLM inference and fine-tuning on Intel XPU platforms, contributing to notable open-source projects like intel/ipex-llm by integrating FastChat, adding XPU support, and improving Docker-based serving workflows. Comfortable bridging research and production, he has practical experience modifying packaging and runtime arguments to make large-model tooling more deployable across diverse hardware. Currently based in Suzhou (originally from Shandong) for a semester due to visa constraints, he is seeking software engineering internship opportunities that leverage his deployment-first approach to ML systems.
3 years of coding experience
Bachelor's degree, Computer Science and technology, Bachelor's degree, Computer Science and technology at 英国利物浦大学Master's degree, Software Engineering, Master's degree, Software Engineering at 美国杜克大学学士, Computer Engineering, 学士, Computer Engineering at 西交利物浦大学
Stackoverflow
1reputation
0reached
1answer
0questions
Github Skills (9)
pytorch10
python10
llm10
dockers9
gpu9
transformers9
docker9
wxwidgets6
importerror6
Programming languages (7)
Github contributions (5)
intel/ipex-llm
Aug 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:
Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:175 reviews, 70 commits, 417 PRs in 4 months
Contributions summary:Guancheng integrated FastChat as a serving framework for BigDL-LLM, implementing features for BigDL-LLM. They added XPU support for FastChat and modified the setup.py dependency installs. They also added features related to Docker serving images by adding vllm worker related arguments. These changes indicate a focus on integrating BigDL-LLM with serving frameworks and improving deployment capabilities.
llm-inferencellama2pythonfinetuningllama
analytics-zoo/FastChat
Aug 2023 - May 2024
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Contributions:16 reviews, 15 PRs, 65 pushes in 9 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.