MasterJH5574 opened a new pull request, #14197: URL: https://github.com/apache/tvm/pull/14197
PR #14067 introduces the flag `keep_params_as_input` to the FX translator, in the purpose to handle to model weights outside of the translated Relax function. This PR takes a further step, by returning the model weights as NDArrays when the flag `keep_params_as_input` is true. With this PR, the translator now can return back the weights upon requested. Otherwise, after the import we will lose the model weights in the given PyTorch model. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
