piwheels

gptqmodel

Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.

Installation

In a virtualenv (see these instructions if you need to create one):

pip3 install gptqmodel

Releases

Version	Released	Bullseye Python 3.9	Bookworm Python 3.11	Files
2.1.0	2025-03-13

2.0.0	2025-03-03

1.9.0	2025-02-12

1.8.1	2025-02-08

1.8.0	2025-02-07

1.7.4	2025-01-26

1.7.3	2025-01-21

1.7.2	2025-01-19

1.7.0	2025-01-17

1.6.0	2025-01-06

1.5.1	2025-01-01

1.5.0	2024-12-24

1.4.5	2024-12-19

1.4.4	2024-12-17

1.4.3	2024-12-17

1.4.2	2024-12-16

1.4.1	2024-12-13

1.4.0	2024-12-10

1.3.1	2024-11-29

1.3.0	2024-11-27

1.2.3	2024-11-25

1.2.1	2024-11-11

1.2.1.dev0 pre-release	2024-11-11

1.2.0	2024-11-11

1.1.0	2024-10-29

1.0.9	2024-10-13

1.0.8	2024-10-11

1.0.7	2024-10-08

1.0.6	2024-09-26

1.0.5	2024-09-26

1.0.4	2024-09-26

1.0.3	2024-09-19

1.0.2	2024-08-17

1.0.1	2024-08-15

Issues with this package?

Search issues for this package
Package or version missing? Open a new issue
Something else? Open a new issue

Page last updated 2025-03-13 18:49:08 UTC