[Bug] run device is wrong

[Winnie202]

Checklist

• [X] I have searched related issues but cannot get the expected help.
• [X] 2. I have read the FAQ documentation but cannot get the expected help.
• [X] 3. The bug has not been fixed in the latest version.

Describe the bug

import torch from mmdeploy.backend.tensorrt import TRTWrapper engine_file = 'tensorrt/edvr_new_batch20.trt' model = TRTWrapper(engine_file,device_id=1) inputs = dict(input=torch.randn(2,3, 3, 288, 352).cuda()) outputs = model(inputs) print(outputs)

I set gpu device=1，but run device is 0

Reproduction

import torch from mmdeploy.backend.tensorrt import TRTWrapper engine_file = 'tensorrt/edvr_new_batch20.trt' model = TRTWrapper(engine_file,device_id=1) inputs = dict(input=torch.randn(2,3, 3, 288, 352).cuda()) outputs = model(inputs) print(outputs)

Environment

openmim                       0.3.9
mmcv                          2.0.0rc4
mmdeploy                      1.3.1
mmdeploy-runtime-gpu          1.3.1
tensorrt                      8.5.1.7

Error traceback

No response