GPU accelerated decision optimization

Portable GPU Programming

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.

Measure and optimize the energy consumption of your AI applications!

Efficient AI-Enhanced 5G PUSCH Receiver

Efficient AI-Enhanced 5G PUSCH Receiver

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

A curated list of materials on AI efficiency

Python code for "Probabilistic Machine learning" book by Kevin Murphy

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

Fast low-bit matmul kernels in Triton

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

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

Neural network quantization for research and prototyping

Real-Time Inference of 5G NR Multi-user MIMO Neural Receivers

Complete solutions to the Programming Massively Parallel Processors Edition 4

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

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

Inference Llama 2 in one file of pure C

Sionna Research Kit: A GPU-Accelerated Research Platform for AI-RAN

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

Course materials for MIT6.5940: TinyML and Efficient Deep Learning Computing

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

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