Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.
Published
March 19, 2026
43d ago
Package Registry
README badge Customize →
License Sources
| Source | License | Class |
|---|---|---|
Licensie (detected) | Apache-2.0 | Permissive |
PyPI (reported) | Not reported | - |
No license was reported in the package metadata for this version.
Loading dependencies…
License File
Added Removed Expected