Yang Wang
Portland, Oregon, United States
Summary
🤩
Rockstar🎓
Top SchoolYang Wang is a seasoned technical leader with over two decades of deep expertise in CPU/SOC validation, software tooling, and program delivery, currently based in Portland, Oregon. He has driven architecture and development of converged validation tools and emulation content for Intel data center and client processors, blending low-level C/C++/IA assembly work with LLVM-based toolchains and linker/memory subsystem expertise. As a hands-on tech lead and program manager he has led multi-site teams using SAFe/Agile to deliver time-critical validation software and test frameworks across OS and bare-metal environments. His background spans pre-silicon and post-silicon debug, PCIe and virtualization features, and process improvements as a certified Lean Six Sigma Green Belt. More recently he has contributed ML-focused optimizations to Intel’s ipex-llm project, improving quantization and attention memory handling for long-sequence LLM performance on Intel XPU hardware—an example of his adaptability moving from silicon validation into emerging ML infrastructure.
10 years of coding experience
31 years of employment as a software developer
Bachelor of Science (BS) Physics/EE, Bachelor of Science (BS) Physics/EE at Peking University, ChinaMaster of Science (M.S.) Physics, Master of Science (M.S.) Physics at The University of AkronMaster of Science (MS) Computer Science, Master of Science (MS) Computer Science at Cleveland State University
Github Skills (5)
transformers10
pytorch10
gpu10
model-optimization10
llm10
Programming languages (5)
Github contributions (5)
intel/ipex-llm
Mar 2017 - 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:
ML Engineer
ML EngineerContributions:482 reviews, 1838 commits, 547 PRs in 5 years 10 months
Contributions summary:Yang primarily focused on enhancing the `ipex-llm` repository with features related to large language models (LLMs). Their contributions included adding API documentation, improving 4-bit quantization for Hugging Face transformers, and optimizing memory usage. Further work involved optimizing Llama and ChatGLM2 attention mechanisms to reduce KV cache memory copy and improve long sequence performance.
llm-inferencellama2pythonfinetuningllama
yangw1234/intel-extension-for-pytorch
Apr 2021 - May 2024
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
Contributions:1 release, 4 pushes, 3 branches in 3 years 1 month
pytorchamdpythondeep-learningintel
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.