Dandi Ding
Researcher at Tencent
Minhang District, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolDandi Ding is a researcher and HPC-focused software engineer with 13 years of experience, currently building high-performance inference infrastructure at Tencent. He specializes in back-end integration and cross-platform optimization, notably wrapping Intel OpenVINO into the widely used Tencent TNN deep learning inference framework to extend x86 and macOS support. His work blends systems-level code changes, performance tuning, and practical deployment experience across mobile, desktop and server environments. Dandi combines industrial R&D experience from Tencent with internships at Ant Financial, Intel, and Baidu, and holds an MEng in Computer Science from Shanghai Jiao Tong University. Colleagues rely on him for pragmatic solutions that bridge open-source frameworks and production constraints, often surfacing non-obvious compatibility and compilation fixes that keep large-scale apps running.
13 years of coding experience
1 year of employment as a software developer
Master of Engineering - MEng, Computer Science, Master of Engineering - MEng, Computer Science at Shanghai Jiao Tong University
Github Skills (7)
c-language10
cprogramming-language10
openvino10
x8610
cmake9
opencl5
tensorrt5
Programming languages (4)
Github contributions (5)
Tencent/TNN
Jun 2020 - Jan 2023
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
Role in this project:
Back-end Developer & OpenVINO Integration Engineer
Back-end Developer & OpenVINO Integration EngineerContributions:51 reviews, 197 commits, 82 PRs in 2 years 7 months
Contributions summary:Dandi primarily focused on integrating the OpenVINO framework into the TNN deep learning inference framework, specifically targeting the x86 CPU platform. Their contributions involved wrapping OpenVINO within TNN, which included modifications to the core network code to facilitate OpenVINO's use. The work involved adapting existing code to incorporate and utilize OpenVINO's inference capabilities, suggesting a focus on optimizing and expanding TNN's support for diverse hardware platforms. Further work added x86 MacOS support and addressed compilation issues.
ncnnuniformtensorflowpituperformance-optimization
bluaxe/minix
Mar 2013 - Jul 2014
Contributions:44 commits in 1 year 4 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.