Driss Guessous's Projects
The torchao repository contains api's and workflows for quantization and pruning gpu models.
TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.
Final Project for CS 513 Data Curation
Training materials associated with NVIDIA's CUDA Training Series (www.olcf.ornl.gov/cuda-training-series/)
cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it
CUDA Templates for Linear Algebra Subroutines
Different projects in data science
DCGAN PROJECT
Cuda extensions for PyTorch
A place to share my DataScience Projects
C++ extensions in PyTorch
Fast and memory-efficient exact attention
A small classifier and server
Topic Modelling for Humans
Compiler for Neural Network hardware accelerators
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Simple (fast) transformer inference in PyTorch with torch.compile + lit-llama code
This is my current playlist and order of operations for setting up new Mac OS computer dev environment.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
2d wave equation simulator
Learnings + Exercises from the PMPP book!
Predict Stocks Market Machine Learning
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
A native PyTorch Library for large model training