TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Libraries and state-of-the-art automatic sparsification algorithms to simplify and accelerate performance

Easy-to-use autoML interface to optimize deep neural networks for better inference performance and a smaller footprint.

CPU inference engine that delivers unprecedented performance for sparse models

An Ansible role for setting up zsh and oh-my-zsh. It will add the themes 'spaceship' and 'bullet-train' (used) as well as some useful configs.

⚡️Data & models versioning for ML projects, make them shareable and reproducible

🔗DVC website and documentation source code

Source for docs.vespene.io, source lives in the main Vespene repo's "docs" folder.

Recurrent neural network for audio noise reduction

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)

Container to easy build stuffs for Python in another containers

auto-tuning momentum SGD optimizer