Hi👋, I'm Chenghua Wang, currently a postgraduate CS student at BUPT.
- I'm interested in AI&Sys.
- I am currently working on MLLM project.
- I've struggled for almost one and half years on computer vision(Dehazing, Multi-label classification. July 1 2021 -> Dec 31 2022)
contact me: [email protected]
Languages used: c, c++, python, golang, asm(x86, risc-v), cuda, glsl, lua, dart
Skills: pytorch, paddlepaddle, opencv, opengl, mysql, redis, flutter, nginx, django
[Projects(click to expand)]
You can visit about for more information.
-
fast and lightweight multimodal LLM inference engine for mobile and edge devices
-
Neural Network inference&compile toolchain for Computer Vision. Still on working.
-
A Matrix lib based on SIMD and expression template. On CPU/GPU. Currently, GPU functionality is not fully implemented
-
A tool for managing distributed database, gathering/cleaning data, etc. covalentBond(cb) using Op graph concept to allow users to easily build query logic and data manipulation logic. We took a lot of inspiration from torch and bound most of cb's operators in lua, making it very easy for users to construct and overload the basic behavior of graphs. This project is for 2022-2023 Fall, SE lecture.
-
A render lib. For 2022-2023 Fall, CG lecture
-
Some notes of papars I read, and some tech report. Including topics: Distributed system, Machine learning system(compiler), HPC, AI
-
A tech report of my image dehazing research from Jan 1 2022 to Dec 31 2022
get in touch. [email protected]