MLX: An array framework for Apple silicon

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

Inference Llama 2 in one file of pure C

Universal cross-platform tokenizers binding to HF and sentencepiece

The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

A framework for few-shot evaluation of autoregressive language models.

CUDA Templates for Linear Algebra Subroutines

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

On-device AI across mobile, embedded and edge for PyTorch

Minimalistic large language model 3D-parallelism training

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Robust recipes for to align language models with human and AI preferences

OmniQuant is a simple and powerful quantization technique for LLMs.

Generative Models by Stability AI

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Train transformer language models with reinforcement learning.

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Port of Facebook's LLaMA model in C/C++

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

High-Resolution Image Synthesis with Latent Diffusion Models