ExecuTorch: Enabling On-Device interference for embedded devices

Re:ExecuTorch: Enabling On-Device interference for embedded ... by mlmandude on Tuesday October 17, 2023 @05:37PM (#37921951)

It looks like executorch is for edge devices (phones / IoT / etc).

I'm currently doing inference on GPUs for libtorch and have a few concerns: (1) It seems like libtorch/torchscript are on a path to getting deprecated and (2) libtorch/torchscript pull in enormously bloated libraries. Should I be looking at executorch? I currently don't see an nvidia backend / integration with tensor rt in https://github.com/pytorch/executorch/tree/main/backends , but seems like it might be possible. Is this something you are thinking about?

[ Parent | on HN ]

Re:ExecuTorch: Enabling On-Device interference for embedded ... by iseeyuan on Tuesday October 17, 2023 @06:56PM (#37922665)

Yes ExecuTorch is currently targeted at Edge devices. The runtime is written in C++ with 50KB binary size (without kernels) and should run in most of platforms. You are right that we have not integrated to Nvidia backend yet. Have you tried torch.compile() in PyTorch 2.0? It would do the Nvidia optimization for you without Torchscript. If you have specific binary size or edge specific request, feel free to file issues in https://github.com/pytorch/executorch/issues

[ Parent | on HN ]

Re:ExecuTorch: Enabling On-Device interference for embedded ... by fooblaster on Tuesday October 17, 2023 @10:04PM (#37924076)

torch.compile only works with python from what I understand. Many people need a native way to run GPU models, but don't want the bloat of full libtorch.

[ Parent | on HN ]