lhutton1 opened a new pull request, #12317: URL: https://github.com/apache/tvm/pull/12317
During compilation of an NPU subgraph, the input and output tensor ordering is determined by creating a mapping of Support Library buffers to TVM buffers. The runtime had been using this mapping incorrectly by instead interpreting it as a mapping of TVM buffers to support library buffers. This can result in undefined behavior. The runtime now interprets the mapping as Support Library buffers to TVM buffers. A test has been added to check the correct ordering of outputs is provided correctly in the runtime. cc @leandron @manupa-arm @Leo-arm -- 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]
