Metadata-Version: 2.4
Name: ssp4onnx
Version: 1.0.1
Summary: Simple Split for ONNX. A simple tool that automatically splits ONNX models of specified weight sizes.
Keywords: onnx,deep-learning,machine-learning
Author: Katsuya Hyodo
Author-email: Katsuya Hyodo <rmsdh122@yahoo.co.jp>
License-Expression: MIT
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: Unix
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Dist: numpy==1.26.4
Requires-Dist: onnx==1.20.1
Requires-Dist: onnx-graphsurgeon==0.5.8
Requires-Python: >=3.10.12
Project-URL: Homepage, https://github.com/PINTO0309/ssp4onnx
Project-URL: Repository, https://github.com/PINTO0309/ssp4onnx
Project-URL: Documentation, https://github.com/PINTO0309/ssp4onnx#readme
Description-Content-Type: text/markdown

# ssp4onnx
**S**imple **Sp**lit for ONNX. A simple tool that automatically splits ONNX models of specified weight sizes.

## Usage
```bash
ssp4onnx -i model.onnx --auto_split_max_size 100MB
```

Options:
- `-i/--input_onnx_file`: input ONNX file (required)
- `-o/--output_dir`: output directory (optional, default: same directory as input)
- `-s/--auto_split_max_size`: target partition size, supports `KB`, `MB`, `GB` (default: `100MB`)

<img width="539" height="330" alt="image" src="https://github.com/user-attachments/assets/6779d186-3f4c-4f5c-b860-49ffc2843967" />
