Quick Start

The following instructions assume you have installed the Intel® Extension for PyTorch*. For installation instructions, refer to Installation.

To start using the Intel® Extension for PyTorch* in your code, you need to make the following changes:

Import the extension with import intel_extension_for_pytorch as ipex.
Move model and data to GPU with to('xpu'), if you want to run on GPU.
Invoke the optimize() function to apply optimizations.
For TorchScript, invoke torch.jit.trace() and torch.jit.freeze().

Important: It is highly recommended to import intel_extension_for_pytorch right after import torch, prior to importing other packages.

The example below demostrates how to use the Intel® Extension for PyTorch*:

import torch
import intel_extension_for_pytorch as ipex

model = Model()
model.eval() # Set the model to evaluation mode for inference, as required by ipex.optimize() function.
data = ...
dtype=torch.float32 # torch.bfloat16, torch.float16 (float16 only works on GPU)

##### Run on GPU ######
model = model.to('xpu')
data = data.to('xpu')
#######################

model = ipex.optimize(model, dtype=dtype)

########## FP32 ############
with torch.no_grad():
####### BF16 on CPU ########
with torch.no_grad(), with torch.cpu.amp.autocast():
##### BF16/FP16 on GPU #####
with torch.no_grad(), with torch.xpu.amp.autocast(enabled=True, dtype=dtype, cache_enabled=False):
############################
  ###### Torchscript #######
  model = torch.jit.trace(model, data)
  model = torch.jit.freeze(model)
  ###### Torchscript #######

  model(data)

More examples, including training and usage of low precision data types are available at Examples.

Execution

Execution requires an active Intel® oneAPI environment. Suppose you have the Intel® oneAPI Base Toolkit installed in /opt/intel/oneapi directory, activating the environment is as simple as sourcing its environment activation bash scripts.

There are some environment variables in runtime that can be used to configure executions on GPU. Please check Advanced Configuration for more detailed information.

source /opt/intel/oneapi/compiler/latest/env/vars.sh
source /opt/intel/oneapi/mkl/latest/env/vars.sh
python <script>