Ferdinand Mom's Projects
My website
Accelerated First Order Parallel Associative Scan
This project accelerates CNN computation with the help of FPGA, for more than 50x speed-up compared with CPU.
Implementation of RAFT
Implementation of https://srush.github.io/annotated-s4
Implementation of Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems. 2017.
An easy-to-use model quantization package with user-friendly apis, based on GPTQ algorithm.
Minimalist ML framework for Rust
Identify the type of disease present on a Cassava Leaf image
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
A Numpy implementation of a Convolutional Neural Network: slow & fast (im2col/col2im).
Making large AI models cheaper, faster and more accessible
Programming homework for the principles and techniques of compilers course in USTC, autumn 2019. Contact me if you're TA or supervisor of this course and want this removed.
Coursera Lab Assignments of "Machine Learning" and "Deep Learning Specialization".
🍮 Online machine learning in Python
Data Structures and Algorithms in C++ (CS225, UIUC)
CS4180 - Deep Learning Project at TU Delft, Netherlands
Toy programming language to ARM Assembly compiler written for CS4212 Compiler Design
Raytracer in CUDA
Prior-Guided One-Shot NAS for CVPR22 Workshop
Computer Vision Tool Library
DA2Lite is an automated model compression toolkit for PyTorch.
Analyse de données ouvertes
torch implementation of diloco