huajsj commented on a change in pull request #8497:
URL: https://github.com/apache/tvm/pull/8497#discussion_r672780360
##########
File path: src/runtime/graph_executor/graph_executor.cc
##########
@@ -389,6 +434,13 @@ void GraphExecutor::SetupOpExecs() {
input_dltensors_[eid].push_back(static_cast<DLTensor*>(op_args->arg_values[i].v_handle));
}
}
+ // check if op output is model output
+ if (output_node_id.count(nid) > 0) {
+ for (uint32_t index = inode.inputs.size();
+ index < inode.param.num_outputs + inode.param.num_inputs; ++index) {
+
output_dltensors_.push_back(static_cast<DLTensor*>(op_args->arg_values[index].v_handle));
Review comment:
there is an hiding assumption for ouput index and entryid relation but
that is not guaranteed, for such case ' "heads": [ [48, 0, 0], [36, 0, 0]],
the said logic would wrong.
--
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]
