Package profile
GPTQModel
- Summary: Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.
- Author: ModelCloud <qubitium@modelcloud.ai>
- License: Apache-2.0
- Homepage: https://github.com/ModelCloud/GPTQModel
- Source: https://github.com/ModelCloud/GPTQModel
- Number of releases: 63
- First release: 1.0.1 on 2024-08-15
- Latest release: 7.5.0 on 2026-09-15
- Latest release size: 1.3 MB (sdist)