Ubospica opened a new pull request, #15224: URL: https://github.com/apache/tvm/pull/15224
Previously `tvm.relax.analysis.estimate_memory_usage` will ignore `R.builtin.alloc_tensor` operators when calculating memory usage of the module **after** memory planning. However, such operators indeed increases the memory usage. This PR will take such operators into account so as to get correct memory statistics. -- 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]
