Ning An
System Engineers at qingcloud.com
Guangdong Province, China
Summary
🤩
Rockstar🎓
Top SchoolNing An is a seasoned system engineer with 14 years' experience building and operating large-scale infrastructure across companies like QingCloud, Baidu, Alibaba, Douban and Xunlei. Strong in C, Perl and Python, he blends low-level systems programming with database administration and CDN and VPS platform expertise, often focusing on automation, monitoring and reliability. Recently he contributed as an MLOps engineer to Xinference, improving inference benchmarking, long-context generation and operational guardrails for running open-source LLMs—showing a practical bent toward ML deployment. Based in Guangdong, China, Ning pairs hands-on implementation skills with a habit of improving performance and observability, making complex systems more efficient and easier to manage.
14 years of coding experience
6 years of employment as a software developer
bachelor, computer science, bachelor, computer science at University of Electronic Science and Technology of China
Stackoverflow
88reputation
61kreached
8answers
2questions
Github Skills (19)
pytorch10
benchmark10
deploying10
apidoc10
python10
benchmarking10
inference10
api10
llm9
machine-learning9
docker8
dockers8
coroutines6
linker6
xen6
Programming languages (7)
Github contributions (5)
xorbitsai/inference
Apr 2024 - Nov 2024
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.
Role in this project:
MLOps Engineer
MLOps EngineerContributions:17 reviews, 25 PRs, 3 pushes in 6 months
Contributions summary:Ning primarily focused on improving the benchmark for inference performance, adding features like long context generation and API key support, and enhancing the system's overall efficiency. They implemented enhancements to the benchmark scripts, including the addition of new features, and addressed issues related to flexible model registration within the worker. Furthermore, the user made improvements to logging, added guardrails for model launching, and refined model termination processes. Their work reflects a strong emphasis on benchmarking, performance optimization, and improving the overall operational aspects of the inference system.
artificial-intelligencechatglmdeploymentflan-t5gemma
frostyplanet/inference
Apr 2024 - Nov 2024
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.
Contributions:99 pushes, 46 branches in 6 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.