Cengguang Zhang
AI Framework Engineer at 英特尔
Minhang District, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolCengguang Zhang is an AI Framework Engineer with nine years of experience, currently building and optimizing AI runtimes at Intel in Shanghai. He holds an MPhil in Computer Science & Engineering from HKUST and a bachelor’s in Computer Science with a big-data focus from Fudan, combining rigorous research training with practical systems expertise. At Intel he focuses on AI framework and inference acceleration, and has contributed technical documentation to the popular intel/ipex-llm project that helps run local LLMs across Intel XPUs and diverse toolchains. Comfortable bridging code and developer experience, he improves adoption by writing clear how-tos, reorganizing guides, and polishing quickstarts. Known for a pragmatic, open mindset—“keep your options open”—he blends engineering depth with attention to developer-facing details that make complex ML stacks usable.
9 years of coding experience
Master of Philosophy - MPhil, Computer Science & Engineering, Master of Philosophy - MPhil, Computer Science & Engineering at 香港科技大学学士学位, 计算机科学与技术（大数据方向）, 学士学位, 计算机科学与技术（大数据方向） at 复旦大学
Github Skills (3)
documentation10
restructuredtext9
rs9
Programming languages (6)
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:187 reviews, 48 commits, 235 PRs in 5 months
Contributions summary:Cengguang primarily contributed to documentation, focusing on refining and expanding the "Orca" section within the repository's documentation. They added how-to guides, updated the sidebar and quickstart order, and made several typo fixes. Their contributions included updating documentation structure and content, specifically for the "Orca" project, and involved modifying various documentation files.
llm-inferencellama2pythonfinetuningllama
lalalapotter/ipex-llm
Mar 2024 - Jan 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:87 pushes, 23 branches 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.