1
$\begingroup$

From my limited understanding, it's quite annoying trying to deploy models like PyTorch. So one would need something like ONNX.

But another approach like Golang with a single binary is VERY attractive. I have used Golang before and it's reasonably fast and compiles to one binary easily. For Rust, compiling to a single binary is a nightmare.

So I wonder if anyone has seen work that translates XGBoost trees to Golang and uses arrow as the data exchange format? That way, it makes deployment super easy, wouldn't it?

$\endgroup$
2
  • $\begingroup$ Have you looked at BentoML? $\endgroup$ Apr 23, 2021 at 13:40
  • $\begingroup$ I dont need a service. I already have a service, I just need the deployment artifact. $\endgroup$
    – xiaodai
    Apr 25, 2021 at 12:02

1 Answer 1

1
$\begingroup$

I code up a Golang package call gotch that can take Pytorch pretrained model and do further training/finetuning or inferring. Have a look at “example” subfolder as well as Gophernotes notebook links in README.md.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.