Efficient Triton Kernels for LLM Training

High-resolution models for human tasks.

An extremely fast Python package and project manager, written in Rust.

A modular graph-based Retrieval-Augmented Generation (RAG) system

A native PyTorch Library for large model training

This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]

maximal update parametrization (µP)

Typer, build great CLIs. Easy to code. Based on Python type hints.

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

Official repository of the xLSTM.

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Containers for machine learning

Your image is almost there!

ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).

streamline the fine-tuning process for multimodal models: PaliGemma, Florence-2, and Qwen2-VL

tiny vision language model

Kolmogorov Arnold Networks

The official Meta Llama 3 GitHub site

Approaching (Almost) Any Machine Learning Problem

Optax is a gradient processing and optimization library for JAX.

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Schedule-Free Optimization in PyTorch

Trio – a friendly Python library for async concurrency and I/O

A Data Streaming Library for Efficient Neural Network Training

An Extensible Deep Learning Library

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

A collection of learning resources for curious software engineers

Universal Tensor Operations in Einstein-Inspired Notation for Python.