Guoqiong Song
Senior Software Engineer at Intel Corporation
Milpitas, California, United States
Summary
🤩
Rockstar🎓
Top SchoolGuoqiong Song is a Senior Software Engineer at Intel with a Ph.D. in Atmospheric and Oceanic Sciences and eight years of experience applying quantitative modeling, machine learning, and big-data analytics to real-world problems. He blends deep domain expertise in climate and remote sensing with production ML engineering—contributing to Intel's ipex-llm to optimize and enable LLM inference/finetuning on Intel XPU hardware. Previously he translated atmospheric modeling skills into telecom-scale data science at Verizon, giving him strength in scalable data pipelines and statistical predictive modeling. Comfortable bridging research and product, he routinely adapts cutting-edge transformer libraries for deployment and streaming use cases. Based in Milpitas, CA, he brings a rare combination of numerical modeling rigor and hands-on systems optimization for ML workloads.
8 years of coding experience
9 years of employment as a software developer
University of California, Los Angeles
English, Chinese
Stackoverflow
21reputation
0reached
2answers
0questions
Github Skills (14)
transformers10
pytorch10
integrate10
gpu10
python10
integrations10
data-integration10
model-optimization10
llm10
cpu9
bigdl6
machine-learning6
analytics-zoo6
classification6
Programming languages (3)
Github contributions (5)
intel/ipex-llm
Dec 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:20 reviews, 107 commits, 150 PRs in 5 years 1 month
Contributions summary:Guoqiong primarily contributes to integrating and implementing Large Language Models (LLMs) on Intel XPU. Their work includes adding examples for running different LLM models like Aquila, Dolly, and others using the BigDL-LLM framework and transformers. They address issues related to model compatibility and performance, incorporating optimizations for GPU and CPU environments, and specifically focus on enabling streaming LLM functionality. The user is also involved in adapting the code for newer versions of the transformer libraries and fixing model-specific integration issues.
llm-inferencellama2pythonfinetuningllama
songhappy/BigDL
Nov 2017 - Sep 2024
BigDL: Distributed Deep Learning Library for Apache Spark
Contributions:2 PRs, 426 pushes, 77 branches in 6 years 10 months
bigdldeep-learningmachine-learningapachespark
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.