Funtowicz Morgan

HMLL - High-Performance Model Loading Library for Efficient AI Model I/O

Language Model Intermediate Representation

PyTorch RNet implementation with Distributed and Mixed-Precision training support.

Lightning Fast LLM Tokenizer

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 efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

No description.

LLM inference in C/C++

No description.

Experiment tracking for hmll repository - exploring not so clear paths and ideas that leads certainly nowhere

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

No description.

The fastest way to install llama.cpp

Accessible large language models via k-bit quantization for PyTorch.

Pure C based implementation of safetensors deserialization

"AI-Trader: Can AI Beat the Market?" Live Trading: https://hkuds.github.io/AI-Trader/

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Turn your Raspberry Pi into a powerful weather station

No description.

2D Cutting Problem solution generator using metaheuristic methods and linear programming

No description.

Automatically generates Rust FFI bindings to C (and some C++) libraries.

AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

The Triton backend for the ONNX Runtime.

Open standard for machine learning interoperability

Flax is a neural network library for JAX that is designed for flexibility.

Fast BPE

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

An open source AutoML toolkit for neural architecture search and hyper-parameter tuning.

Pervasive Attention: 2D Convolutional Networks for Sequence-to-Sequence Prediction

Spik Android application

No description.

PyTorch implementation of Advantage async actor-critic Algorithms (A3C) in PyTorch

Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:

Lakka is a lightweight Linux distribution that transforms a small computer into a full blown game console.

Dofus NotificationsCenter module