# OpenPPL/ppq

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Repository: https://github.com/OpenPPL/ppq
Canonical: https://ross.abutalabs.com/products/ppq
Language: Python
License: Apache-2.0
License Family: permissive
Topics: neural-network, deep-learning, quantization, pytorch, caffe, onnx, cuda, open-source
Last push: 2024-03-28T04:26:28+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1707, "days_push": 888, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1816, forks 285 (observed 2026-08-28T04:05:40.074513+00:00)

## What it is
PPQ (PPL Quantization Tool) is an extensible, high-performance offline neural network quantization framework written in Python. It parses and quantizes complex model graphs (ONNX, PyTorch, Caffe), supports FP8 and QAT, and exports to inference engines like TensorRT, OpenPPL, OpenVINO, ncnn, and SNPE.

## Use cases
- quantize a neural network model for edge deployment
- convert an onnx model to int8 for tensorrt
- simulate quantized inference on different hardware platforms
- perform quantization-aware training on a model
- calibrate quantization parameters for a custom accelerator
- export a quantized model to ncnn or openvino

## When to choose
- you need fine-grained control over per-operator quantization settings and custom quantization passes
- you target multiple inference backends like TensorRT, OpenPPL, ncnn, or SNPE
- you need FP8 or QAT support alongside standard PTQ calibration
- you want to experiment with quantization research on custom hardware

## When to avoid
- you just need simple one-click post-training quantization with minimal configuration
- your workflow is TensorFlow-only, since PPQ focuses on ONNX, PyTorch, and Caffe
- you need a maintained tool with frequent releases, as the latest release dates to early 2024

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, compiler, benchmarking, parser
- domain: deep-learning, machine-learning, gpu-computing, developer-tools
- platform: python, windows
- tags: quantization, model-optimization, onnx, pytorch, inference-deployment, qat, fp8, neural-network-acceleration, linux, cuda, gpu

## Member repositories
- OpenPPL/ppq (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:40.074513+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:20:34.515397+00:00, confidence not recorded.
  - readme: https://github.com/OpenPPL/ppq (fetched 2026-08-28T04:05:40.074513+00:00, sha 874c2b59348e)
- Data as of 2026-08-30T08:39:29.467469+00:00.