❓ [Question] Why import torch_tensorrt set log level to info automatically?

[KindRoach]

❓ Question

The default log level of python is warning. Why import torch_tensorrt set log level to info automatically? How could I set log level back to warning?

import logging
import torch_tensorrt

logging.info("INFO")
logging.warning("WARNING")
logging.error("ERROR")

stderr outputs:

INFO:root:INFO
WARNING:root:WARNING
ERROR:root:ERROR

what I want:

WARNING:root:WARNING
ERROR:root:ERROR

What you have already tried

Below statements doesn't work

torch_tensorrt.logging.set_reportable_log_level(torch_tensorrt.logging.Level.Warning)
# or
logging.basicConfig(level=logging.WARNING)

Environment

Build information about Torch-TensorRT can be found by turning on debug messages

Docker image from: nvcr.io/nvidia/pytorch:23.05-py3

[apbose]

May I know how are you compiling the model. Generally for specifying the log level you need to specify the log level like this -

 with torch_tensorrt.logging.warnings():
        model_trt = torch_tensorrt.compile(model, **spec)

[github-actions[bot]]

This issue has not seen activity for 90 days, Remove stale label or comment or this will be closed in 10 days