Skip to main content

esp-ppq is an offline quantization tools

Project description

ESP-PPQ Quantization Tool

ESP-PPQ is a quantization tool based on PPQ, and its source code is fully open-sourced. Built upon PPQ, ESP-PPQ adds Espressif-customized quantizers and exporters, allowing users to select quantization rules compatible with ESP-DL for different chips and export standardized model files that can be directly loaded by ESP-DL. ESP-PPQ is fully compatible with all PPQ APIs and quantization scripts.

For more details on quantization principles, please refer to the PPQ documentation and videos. For instructions on using ESP-PPQ, see How to quantize model.

Installation (安装方法)

  1. Install CUDA from CUDA Toolkit

  2. Install Complier

apt-get install ninja-build # for debian/ubuntu user
yum install ninja-build # for redhat/centos user

For Windows User:

(1) Download ninja.exe from https://github.com/ninja-build/ninja/releases, add it to Windows PATH.

(2) Install Visual Studio 2019 from https://visualstudio.microsoft.com.

(3) Add your C++ compiler to Windows PATH Environment, if you are using Visual Studio, it should be like "C:\Program Files\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.16.27023\bin\Hostx86\x86"

(4) Update PyTorch version to >=2.0.0.

  1. Install PPQ

Method 1: Install the package using pip

   pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
   pip install esp-ppq

Method 2: Install from source with pip to stay synchronized with the master branch

   git clone https://github.com/espressif/esp-ppq.git
   cd esp-ppq
   pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
   pip install -e .

Method 3: Install the package using uv

   uv pip install "esp-ppq[cpu]" --torch-backend=cpu
   # GPU
   # uv pip install "esp-ppq[cpu]" --torch-backend=cu124
   # AMD GPU
   # uv pip install "esp-ppq[cpu]" --torch-backend=rocm6.2
   # Intel XPU
   # uv pip install "esp-ppq[cpu]" --torch-backend=xpu

Method 4: Install from source using uv to stay in sync with the master branch

   git clone https://github.com/espressif/esp-ppq.git
   cd esp-ppq
   uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
   uv pip install -e .

Method 5: Use esp-ppq with docker:

docker build -t esp-ppq:your_tag https://github.com/espressif/esp-ppq.git

[!NOTE]

  • The example code installs the Linux PyTorch CPU version. Please install the appropriate PyTorch version based on your actual needs.
  • If installing the package with uv, simply modify the --torch-backend parameter, which will override the PyTorch URLs index configured in the project.

License

This project is distributed under the Apache License, Version 2.0.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

esp_ppq-1.3.2.tar.gz (465.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

esp_ppq-1.3.2-py3-none-any.whl (650.8 kB view details)

Uploaded Python 3

File details

Details for the file esp_ppq-1.3.2.tar.gz.

File metadata

  • Download URL: esp_ppq-1.3.2.tar.gz
  • Upload date:
  • Size: 465.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for esp_ppq-1.3.2.tar.gz
Algorithm Hash digest
SHA256 aa341f7a76f532e1ba64792361d0d5a799a6185e3a91ce4f90fd7ba474d91f50
MD5 1d6106c425737354020cada24c0ca2dd
BLAKE2b-256 f25dcc5c20848e6a33f947de3b3b6759200ffddc64242a0d96b62708e0c1f0cc

See more details on using hashes here.

File details

Details for the file esp_ppq-1.3.2-py3-none-any.whl.

File metadata

  • Download URL: esp_ppq-1.3.2-py3-none-any.whl
  • Upload date:
  • Size: 650.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for esp_ppq-1.3.2-py3-none-any.whl
Algorithm Hash digest
SHA256 6d6f10a61664719f5e5e9a4020d9e96353a7913cceb5d492d57130fd3d3e9c3a
MD5 6a57fe9cd390c8ecb3c27c544de178f9
BLAKE2b-256 a5da6317080da47b6dea67049ddb5695bc1c618bb160c305c1b4253e6052099e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page