Yi-chun Chen
EDA Tools Software Engineer at Intel Corporation
Hillsboro, Oregon, United States
Summary
🤩
Rockstar🎓
Top SchoolYi-chun Chen is an EDA tools software engineer at Intel with over 8 years of experience building and optimizing design automation and backend systems. With a PhD in Physics and an MS in Computer Science from USC, Yi-chun blends deep scientific rigor with practical software engineering to tackle complex performance and tooling challenges. At Intel since 2008 across CAD and EDA roles, they focus on making large-scale workflows reliable and efficient for chip design. An active open-source contributor, Yi-chun has enhanced Intel’s ipex-llm to improve local LLM inference, adding Linux packaging, model quantization, and integrations that bridge ML tooling with hardware accelerators. Comfortable at the intersection of hardware, ML, and software, they bring a pragmatic research mindset to production engineering in Hillsboro, Oregon.
8 years of coding experience
13 years of employment as a software developer
PhD Physics, PhD Physics at University of Southern CaliforniaBS Physics, BS Physics at National Tsing Hua University
Github Skills (13)
llm10
transformers10
quantization10
pytorch10
quants10
gpu10
python10
apidoc9
linux9
api9
documentation8
cprogramming-language7
c-language7
Programming languages (3)
Github contributions (5)
intel/ipex-llm
Jul 2019 - Dec 2022
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:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:228 reviews, 245 commits, 359 PRs in 3 years 5 months
Contributions summary:Yi-chun primarily focused on enhancing the functionality and features of the LLM inference and finetuning tools within the ipex-llm repository. They made updates to the documentation, particularly for integration with the Orca and Friesian APIs. Additionally, they added support for Linux packages, model quantization, and batch actions to the transformers API, improving usability and efficiency of the LLM models. The contributions indicate a focus on making the repository a better tool for running large language models.
llm-inferencellama2pythonfinetuningllama
cyita/BigDL
Mar 2021 - Feb 2025
BigDL: Distributed Deep Learning Framework for Apache Spark
Contributions:662 pushes, 220 branches in 3 years 11 months
bigdldeep-learningapachemachine-learningbig-data
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.