Installation#

Requirements#

  • Python ≥ 3.10

  • PyTorch (the only runtime dependency)

Install#

pip install embedl-deploy

This installs the base package — enough to build models in PyTorch and export to ONNX.

Backend extras#

Each compilation backend is installed as an optional extra:

Extra

Command

Target hardware

tensorrt

pip install "embedl-deploy[tensorrt]"

NVIDIA GPUs

lattice

pip install "embedl-deploy[lattice]"

Lattice FPGAs

The extra pulls in the corresponding companion wheel (embedl-deploy-tensorrt or embedl-deploy-lattice). See Backends for how the active backend is selected at runtime.

For model compilation, you may need additional tools such as TensorRT (trtexec), but these are not required to create deployment-ready models in PyTorch and export them to ONNX.