jinhongyii opened a new pull request, #16049: URL: https://github.com/apache/tvm/pull/16049
In some cases the shape of model weight contains a symbolic var, like vocab size, but it should be treated as if it's constant in LiftTransformParams because it does not change in each call of decode/prefill functions. This PR implements this behavior. -- 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]
