Optimum Python Packages

optimum-quanto

A pytorch quantization backend for optimum

gptqmodel

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

quanto

A pytorch quantization backend for optimum

optimum-transformers

Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.

optimum-grilly

HuggingFace Optimum backend for Grilly — Vulkan GPU inference on any GPU