jroesch commented on a change in pull request #7518:
URL: https://github.com/apache/tvm/pull/7518#discussion_r664940865
##########
File path: include/tvm/relay/attrs/annotation.h
##########
@@ -67,6 +67,18 @@ struct CompilerAttrs : public tvm::AttrsNode<CompilerAttrs> {
}
};
+/*!
Review comment:
Fix the comment here
##########
File path: python/tvm/auto_scheduler/relay_integration.py
##########
@@ -376,6 +377,14 @@ def auto_schedule_topi(func_name, outs):
return schedule
+@tvm._ffi.register_func("auto_scheduler.relay_integration.te_compiler_update_weights")
Review comment:
Add comment here.
##########
File path: python/tvm/micro/model_library_format.py
##########
@@ -156,6 +156,7 @@ def _build_function_memory_map(function_metadata):
2.) A global memory requirement if all functions are executed
sequentially
"""
device_max_workspace = dict()
+ print("TOTAL FUNCTION METADATA: ", function_metadata)
Review comment:
Remove
--
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]
