AIMET Installation
Quick Install
The AIMET PyTorch GPU PyPI packages are available for environments that meet the following requirements:
64-bit Intel x86-compatible processor
Linux Ubuntu 22.04 LTS [Python 3.10] or Linux Ubuntu 20.04 LTS [Python 3.8]
Torch 1.13+cu117
Pip install:
apt-get install liblapacke
python3 -m pip install aimet-torch
Release Packages
For other aimet variants, install the latest version from the .whl files hosted at https://github.com/quic/aimet/releases
PyTorch
# Pytorch 1.13 with CUDA 11.x python3 -m pip install https://github.com/quic/aimet/releases/download/1.31.0/aimet_torch_gpu_1.31.0-cp38-cp38-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html # Pytorch 1.13 CPU only python3 -m pip install https://github.com/quic/aimet/releases/download/1.31.0/aimet_torch_cpu_1.31.0-cp38-cp38-manylinux_2_34_x86_64.whl # Pytorch 2.1 with CUDA 11.x python3 -m pip install https://github.com/quic/aimet/releases/download/1.31.0/aimet_torch_gpu_pt21_1.31.0-cp38-cp38-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html # Pytorch 2.1 CPU only python3 -m pip install https://github.com/quic/aimet/releases/download/1.31.0/aimet_torch_cpu_pt21_1.31.0-cp38-cp38-manylinux_2_34_x86_64.whl
TensorFlow
# Tensorflow 2.10 GPU with CUDA 11.x python3 -m pip install https://github.com/quic/aimet/releases/download/1.31.0/aimet_tensorflow_gpu_1.31.0-cp38-cp38-manylinux_2_34_x86_64.whl # Tensorflow 2.10 CPU only python3 -m pip install https://github.com/quic/aimet/releases/download/1.31.0/aimet_tensorflow_cpu_1.31.0-cp38-cp38-manylinux_2_34_x86_64.whl
Onnx
# ONNX 1.14 GPU python3 -m pip install https://github.com/quic/aimet/releases/download/1.31.0/aimet_onnx_gpu_1.31.0-cp38-cp38-manylinux_2_34_x86_64.whl # ONNX 1.14 CPU python3 -m pip install https://github.com/quic/aimet/releases/download/1.31.0/aimet_onnx_cpu_1.31.0-cp38-cp38-manylinux_2_34_x86_64.whl
For previous AIMET releases, browse packages at https://github.com/quic/aimet/releases. Each release includes multiple python packages of the following format:
# VARIANT in {torch_gpu, torch_cpu, tf_gpu, tf_cpu, onnx_gpu, onnx_cpu}
# PACKAGE_PREFIX in {aimet_torch, aimet_tensorflow, aimet_onnx}
<PACKAGE_PREFIX>-<VARIANT>_<VERSION>-cp38-cp38-manylinux_2_34_x86_64.whl
System Requirements
The AIMET package requires the following host platform setup:
64-bit Intel x86-compatible processor
Linux Ubuntu: 22.04 LTS
bash command shell
- For GPU variants:
Nvidia GPU card (Compute capability 5.2 or later)
nvidia-docker - Installation instructions: https://github.com/NVIDIA/nvidia-docker
To use the GPU accelerated training modules an Nvidia CUDA enabled GPU with a minimum Nvidia driver version of 455+ is required. Using the latest driver is always recommended, especially if using a newer GPU. Both CUDA and cuDNN (the more advanced CUDA interface) enabled GPUs are supported.
Recommended host system hardware requirements:
Intel i7 multicore CPU w/hyperthreading
16+ GB RAM
500GB+ SSD hard drive
- For GPU variants:
GPU: Nvidia GeForce GTX 1080 or Tesla V100
While these are not minimum requirements, they are recommended for good performance when training large networks.
Advanced Installation Instructions
- There are two ways to setup and install AIMET:
On your host machine
Using our pre-built development Docker images
Please click on the appropriate link for installation instructions: