tvm version:v0.13.dev0
I want to tune model for mali gpu follow this guide Auto-scheduling a Neural Network for mali GPU — tvm 0.13.dev0 documentation
And I can successfully get gpu hardware params by:
remote = request_remote(device_key, “127.0.0.1”, 9190)
dev = remote.cl()
But when tune_and_evaluate raise an error: RuntimeError: Cannot get remote devices from the tracker. Please check the status of tracker by ‘python -m tvm.exec.query_rpc_tracker --port [THE PORT YOU USE]’ and make sure you have free devices on the queue status.
The error will not raise for the cpu and the rpc setting checked is ok.