Metadata-Version: 2.4
Name: Qwodel
Version: 1.3.0
Summary: Production-grade model quantization SDK for enterprise custom models (AWQ, GGUF, and CoreML)
Author: Qwodel
Maintainer: Qwodel Contributors
License: Qwodel Community License v1.0
Project-URL: Homepage, https://github.com/YOUR_ORG/qwodel
Project-URL: Documentation, https://qwodel.readthedocs.io
Project-URL: Repository, https://github.com/YOUR_ORG/qwodel
Project-URL: Issues, https://github.com/YOUR_ORG/qwodel/issues
Project-URL: Changelog, https://github.com/YOUR_ORG/qwodel/blob/main/CHANGELOG.md
Keywords: quantization,model-compression,llm,awq,gguf,coreml,machine-learning,enterprise
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: Other/Proprietary License
Classifier: Operating System :: OS Independent
Classifier: Typing :: Typed
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: transformers>=4.51.3
Requires-Dist: huggingface_hub>=0.20.0
Requires-Dist: safetensors>=0.4.0
Requires-Dist: numpy<2.0,>=1.24.0
Requires-Dist: click>=8.0.0
Requires-Dist: rich>=13.0.0
Requires-Dist: requests>=2.31.0
Requires-Dist: tiktoken>=0.5.0
Requires-Dist: sentencepiece>=0.1.99
Provides-Extra: awq
Requires-Dist: torch>=2.10.0; extra == "awq"
Requires-Dist: torchvision>=0.25.0; extra == "awq"
Requires-Dist: torchaudio>=2.10.0; extra == "awq"
Requires-Dist: llmcompressor>=0.2.0; extra == "awq"
Requires-Dist: accelerate>=0.25.0; extra == "awq"
Requires-Dist: optimum>=1.16.0; extra == "awq"
Requires-Dist: datasets>=4.5.0; extra == "awq"
Requires-Dist: zstandard>=0.25.0; extra == "awq"
Provides-Extra: gguf
Requires-Dist: torch>=2.10.0; extra == "gguf"
Requires-Dist: torchvision>=0.25.0; extra == "gguf"
Requires-Dist: torchaudio>=2.10.0; extra == "gguf"
Requires-Dist: gguf>=0.12.0; extra == "gguf"
Requires-Dist: llama-cpp-python>=0.2.23; extra == "gguf"
Provides-Extra: coreml
Requires-Dist: torch>=2.10.0; extra == "coreml"
Requires-Dist: torchvision>=0.25.0; extra == "coreml"
Requires-Dist: torchaudio>=2.10.0; extra == "coreml"
Requires-Dist: coremltools>=8.0.0; extra == "coreml"
Provides-Extra: all
Requires-Dist: qwodel[awq,coreml,gguf]; extra == "all"
Provides-Extra: dev
Requires-Dist: pytest>=7.4.0; extra == "dev"
Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Requires-Dist: mypy>=1.7.0; extra == "dev"
Requires-Dist: pre-commit>=3.5.0; extra == "dev"
Requires-Dist: build>=1.0.0; extra == "dev"
Requires-Dist: twine>=4.0.0; extra == "dev"
Provides-Extra: docs
Requires-Dist: mkdocs>=1.5.0; extra == "docs"
Requires-Dist: mkdocs-material>=9.4.0; extra == "docs"
Requires-Dist: mkdocstrings[python]>=0.24.0; extra == "docs"
Dynamic: license-file

# Qwodel

[![PyPI](https://img.shields.io/pypi/v/qwodel.svg)](https://pypi.org/project/Qwodel/)
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![License: Community](https://img.shields.io/badge/License-Qwodel%20Community%20v1.0-blue.svg)](LICENSE)
[![Docs](https://img.shields.io/badge/docs-docs.qwodel.com-blue.svg)](https://docs.qwodel.com/docs)

Production-grade model quantization SDK for AWQ, GGUF, and CoreML.

## Installation

```bash
# Pick the backend you need
pip install qwodel[gguf]    # CPU quantization
pip install qwodel[awq]     # GPU quantization (requires CUDA)
pip install qwodel[coreml]  # Apple devices
pip install qwodel[all]     # Everything
```

## Quick Example

```python
from qwodel import Quantizer

output = Quantizer(
    backend="gguf",
    model_path="meta-llama/Llama-2-7b-hf",
    output_dir="./quantized"
).quantize(format="Q4_K_M")

print(f"Saved to: {output}")
```

## Documentation

Full documentation — guides, API reference, CLI reference, and examples — is at:

**[docs.qwodel.com/docs](https://docs.qwodel.com/docs)**

## Contributing

See [CONTRIBUTING.md](CONTRIBUTING.md).

## License

Qwodel Community License v1.0 — see [LICENSE](LICENSE).

## Acknowledgments

Built on top of [llama.cpp](https://github.com/ggerganov/llama.cpp), [llm-compressor](https://github.com/vllm-project/llm-compressor), and [CoreMLTools](https://github.com/apple/coremltools).
