Any plan for web support? :)
There's wasi-nn for that I think. Whatever the original question means
ExecuTorch: Run PyTorch programs on mobile and edge devices
21–27 of 27 posts
Re: ExecuTorch: Run PyTorch programs on mobile and edge devices
#22Earlier quoted context omitted.
It looks like executorch is for edge devices (phones / IoT / etc). I'm currently doing inference on GPUs with 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/…
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 issue…
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.
Re: ExecuTorch: Run PyTorch programs on mobile and edge devices
#23The Android example is still too low level and full of CLI stuff, it would be easier for adoption, if it was more focused on Android Studio and building AARs.
Re: ExecuTorch: Run PyTorch programs on mobile and edge devices
#24Hey guys, we are ExecuTorch team, we're excited about launching this! Please ask us anything :)
Is it possible to execute a light weight language model, perhaps this https://github.com/facebookresearch/llama using ExecuTorch to run on smartphone in real time for a chatbot app ? Please share some guidance.
Re: ExecuTorch: Run PyTorch programs on mobile and edge devices
#25Hey guys, we are ExecuTorch team, we're excited about launching this! Please ask us anything :)
We like Rust for its build tooling and safe concurrency primitives. Thus we are eyeballing with candle [1].
OTOH, writing platform specific backends is a huge undertaking. Do you think backends such as MPS may become a shared effort?
[1] https://github.com/huggingface/candle [2] https://github.com/huggingface/candle/issues/313
Re: ExecuTorch: Run PyTorch programs on mobile and edge devices
#26Hey guys, we are ExecuTorch team, we're excited about launching this! Please ask us anything :)
Looks cool! Does the Vulkan backend work on PC? MLC-LLM proves it can work well and it would be cool to have a cross platform, minimal runtime, GPU-agnostic backend for PC too, not just mobile.
The Vulkan backend does work on PC, as the only requirement is that Vulkan drivers are present. However, it was developed with mobile use-cases in mind and we haven't validated/optimized performance for PC.
As an aside, the Vulkan backend is tied to TorchScript at the moment, so it is not yet compatible with ExecuTorch. However, we are also planning to introduce a Vulkan delegate for ExecuTorch which will enable GPU delegation through ExecuTorch.
Re: ExecuTorch: Run PyTorch programs on mobile and edge devices
#27Hey guys, we are ExecuTorch team, we're excited about launching this! Please ask us anything :)
hey - this might be a rather specific use case, but our applications need to run "real-time" and allocation-free - are there any guarantees on that from your side? assuming fixed shapes, pre-allocating everything for the forward pass should probably be possible in theory, but i guess that wasn't really a relevant factor in the design of it all