GPTQModel
Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.
- Latest release
- Jun 08, 2026
- Releases
- 55
- Known CVEs
- 0
- First release
- Aug 15, 2024
- License
- Apache-2.0
Repository
Source
- Stars
- —
- Forks
- —
- Open issues
- —
Security score
No OpenSSF Scorecard available for this repository.
Packages from this repo
No other tracked packages from this repository.
Insights
Activity
- Total releases
- 55
- Last 12 months
- 20
- Cadence
- ~5 days
- Dependencies
- 45
Releases per month
last 12 monthsRelease mix
- major 5
- minor 19
- patch 29
- pre 1
55
releases
Dependencies
Depends on
7.1.0-
accelerate
>=1.13.0
-
bitblas
==0.1.0.post1
-
bitsandbytes
>=0.49.3
-
datasets
>=3.6.0
-
defuser
>=0.0.21
-
device-smi
>=0.5.5
-
dill
>=0.3.8
-
evalution
-
fastapi
-
flashinfer-python
>=0.3.1
1–10 of 45
Used by
Nothing tracked depends on this yet.
Releases
| Version | Released | |
|---|---|---|
7.1.0
minor
| ||
7.0.0
major
| ||
6.0.3
patch
| ||
6.0.0
major
| ||
5.8.0
minor
| ||
5.7.0
minor
| ||
5.6.12
patch
| ||
5.6.10
patch
| ||
5.6.8
patch
| ||
5.6.6
patch
| ||
5.6.2
patch
| ||
5.6.0
minor
| ||
5.4.2
patch
| ||
5.4.0
minor
| ||
5.2.0
minor
| ||
5.0.0
major
| ||
4.2.5
patch
| ||
4.2.0
minor
| ||
4.1.0
minor
| ||
4.0.0
major
|
1–20 of 55