slyubomirsky commented on code in PR #14282:
URL: https://github.com/apache/tvm/pull/14282#discussion_r1134330594
##########
src/runtime/relax_vm/builtin.cc:
##########
@@ -380,6 +380,40 @@
TVM_REGISTER_GLOBAL("vm.builtin.make_tuple").set_body([](TVMArgs args, TVMRetVal
*rv = arr;
});
+TVM_REGISTER_GLOBAL("vm.builtin.tensor_to_shape").set_body_typed([](NDArray
data) {
+ NDArray arr = data;
+ if (data->device.device_type != kDLCPU) {
Review Comment:
I assume it's to avoid data movement if the tensor isn't on CPU. Perhaps we
should incorporate data movement if it's necessary
--
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]
