Nano vLLM

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

Minimalistic 4D-parallelism distributed training framework for education purpose

Everything about the SmolLM & SmolLM2 family of models

A native PyTorch Library for large model training

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Fast and memory-efficient exact attention

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Grok open release

Demonstrate throughput of PyTorch FSDP

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Website for hosting the Open Foundation Models Cheat Sheet.

Modeling, training, eval, and inference code for OLMo

Collection of best practices, reference architectures, model training examples and utilities to train large models on AWS.

Machine Learning Engineering Open Book

Minimalistic large language model 3D-parallelism training

ML/DL Math and Method notes

A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

ImageBind One Embedding Space to Bind Them All

A high-throughput and memory-efficient inference and serving engine for LLMs

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.