Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep lear…

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Digital Communication with Python

Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy.

Summary, Code for Deep Neural Network Quantization

[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers

Fast low-bit matmul kernels in Triton

Implementation of Axial attention - attending to multi-dimensional data efficiently

Measure and optimize the energy consumption of your AI applications!

Code for the book "The Elements of Differentiable Programming".

agent-from-scratch is a Python-based repository designed for developers and researchers interested in understanding the inner workings of single and multi-agent systems

Python for Random Matrix Theory: cleaning schemes for noisy correlation matrices.

Neural network quantization for research and prototyping

Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment

Semi-Supervised End-to-End Learning for Integrated Sensing and Communications

CS433 project. Implement Post-training Quantization method ACIQ and ADAROUND.

Source code of the Paper "Sparse Bayesian Generative Modeling for Compressive Sensing" (NeurIPS 24)

Dorefa、Pact quantization

Efficient Knowledge Injection in LLMs via Self-Distillation (TMLR)

Code for the paper "Cauchy-Schwarz Regularizers" from ICLR 2025

An official implementation of "Scheduling Weight Transitions for Quantization-Aware Training" (ICCV 2025) in PyTorch.

Efficient AI-Enhanced 5G PUSCH Receiver

Efficient AI-Enhanced 5G PUSCH Receiver

A script to perform some simple actions on Spotify API. I was tired of Spotify shuffle so I did my own shuffle.