-
Notifications
You must be signed in to change notification settings - Fork 542
[0.6 documentation] Custom kernels section could provide more steps #10031
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Comments
@kirklandsign are you specifically looking for a description of how they look under the hood, or just how to use them? |
Say I user wants to use these custom kernels, it's hard to follow that section if they are first time using it. I feel like https://pytorch.org/executorch/0.6/kernel-library-custom-aten-kernel.html#custom-kernel-libraries contains more info. Can we just direct to that page? |
I think that makes sense. Do you want to put up a PR and others can review it? |
Yes please. Thank you @kirklandsign ! |
BTW seems that https://pytorch.org/executorch/0.6/llm/getting-started.html#using-a-custom-operator-in-a-model is the only place in the website which mentioned replace_linear_with_custom_linear. |
Looks like this is done now @kirklandsign ? |
📚 The doc issue
In https://pytorch.org/executorch/0.6/llm/getting-started.html#custom-kernels, can we provide more steps on how the yaml codegen and build works?
Suggest a potential alternative/fix
No response
cc @mergennachin @byjlw
The text was updated successfully, but these errors were encountered: