xslim 2.0.12

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_parameters": [{
            "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
• Accuracy Tuning Guide – How to diagnose and improve quantization accuracy

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
2.0.12	Current development version
2.0.11	Latest release; fix Pad/missing-input handling, add Or/Einsum/Selu support, normalize Conv/ConvTranspose kernel shapes, raise minimum Python to 3.9
2.0.10	Align release metadata, improve CI/test coverage, normalize missing default ONNX opset before dynamic quantization, and refine shape inference handling
2.0.9	Add documentation, preserve tensor dtype metadata during FP16 conversion, and restore compatibility with onnxslim 0.1.87
2.0.8	Improve packaging/CI, add torch executor operator coverage, add PyPI publish workflow, and centralize version metadata
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.