PatrikPerssonInceptron opened a new pull request, #17693: URL: https://github.com/apache/tvm/pull/17693
The c++ implementation BindParams can accept tvm.relax.Constants, however the python interface assert only allows ndarrays. I added tvm.relax.Constant to the assert. By allowing tvm.relax.Constants as input arguments to BindParams it is possible to avoid duplicating weights if there are several functions in the module that are using the same weight as an input parameter, such as prefill and decode in an LLM. -- 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]
