ModelCloud/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.

Owner: ModelCloud (organization)
Stars: Stars: 1,283
Forks: Forks: 213
Language: Python
License: None
Created: 2024
Topics: gptqoptimumpeftquantizationsglangtransformersvllm
Tier: Beta (700 to 1,999 ★) What this tier means

View on GitHub

Nearby in Python

All Python repos

kiwitcms/KiwiStars: 1,283PythonBeta
ericyangyu/PPO-for-BeginnersStars: 1,283PythonBeta
mategol/PySilonStars: 1,283PythonBeta
ForensicArtifacts/artifactsStars: 1,283PythonBeta