xslim 2.0.9

XSlim is an offline quantization tools based on PPQ

XSlim

中文版 | English

XSlim is a Post-Training Quantization (PTQ) tool developed by SpacemiT. It integrates chip-optimized quantization strategies and provides a unified interface for ONNX model quantization via JSON configuration files.

---

• Features
• Installation
• Quick Start
• Documentation
• Samples
• Changelog
• Contributing
• License

Features

• INT8 / FP16 / Dynamic Quantization – multiple precision levels for different deployment scenarios
• JSON-driven configuration – simple, declarative quantization setup
• Python API & CLI – use as a library or from the command line
• Custom preprocessing – plug in your own preprocessing functions
• ONNX-based workflow – built on the ONNX ecosystem

Installation

pip install xslim

Or install from source:

git clone https://github.com/spacemit-com/xslim.git
cd xslim
pip install -r requirements.txt

Quick Start

Python API

import xslim

# Using a JSON config file
xslim.quantize_onnx_model("config.json")

# Using a dict
config = {
    "model_parameters": {
        "onnx_model": "model.onnx",
        "working_dir": "./output"
    },
    "calibration_parameters": {
        "input_parametres": [{
            "mean_value": [123.675, 116.28, 103.53],
            "std_value": [58.395, 57.12, 57.375],
            "color_format": "rgb",
            "preprocess_file": "PT_IMAGENET",
            "data_list_path": "./calib_img_list.txt"
        }]
    }
}
xslim.quantize_onnx_model(config)

# You can also pass the model path and output path directly
xslim.quantize_onnx_model("config.json", "input.onnx", "output.onnx")

Command Line

# INT8 quantization with a JSON config
python -m xslim --config config.json

# Specify input and output model paths
python -m xslim -c config.json -i input.onnx -o output.onnx

# Dynamic quantization (no config file needed)
python -m xslim -i input.onnx -o output.onnx --dynq

# FP16 conversion (no config file needed)
python -m xslim -i input.onnx -o output.onnx --fp16

# ONNX simplification only (no config file needed)
python -m xslim -i input.onnx -o output.onnx

Documentation

• Configuration Reference – Full description of all JSON configuration options
• Examples – Step-by-step guides for INT8, FP16, dynamic quantization, custom preprocessing, and more

Samples

See the samples directory for ready-to-run examples covering ResNet-18, MobileNet V3, BERT, and more.

Changelog

For a full list of changes, see the Releases page.

Version	Highlights
2.0.9	Current development version
2.0.8	Latest release
2.0.7	Fix FP16 conversion bug on complex models
2.0.6	Fix metadata props deletion; default CLI behavior changed to model simplification (use --dynq for dynamic quantization)

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

This project is licensed under the Apache License 2.0.