torch_tensor version not support？

[mengchengxxx]

my cuda version:
Thu Mar 30 07:08:20 2023
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 520.61.05 Driver Version: 520.61.05 CUDA Version: 11.8 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... On | 00000000:01:00.0 Off | N/A |
| 0% 44C P8 17W / 170W | 10MiB / 12288MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
+-----------------------------------------------------------------------------+

on docker image:
bladedisc/bladedisc:latest-runtime-torch1.12.0-cu113

run command:
bash benchmark/torch-tensorrt/test_trt_benchmark.sh 2>&1 | tee test_trt.log

error:
======begine================>
Torch-Blade =================================
batch size=1, num iterations=100
Median FPS: 213.5, mean: 213.2
Median latency: 0.004683, mean: 0.004691, 99th_p: 0.004742, std_dev: 0.000027

Running Torch-TensorRT 11111111
Running Torch-TensorRT 22222222
torch_tensorrt failed
compile_graph(): incompatible function arguments. The following argument types are supported:
1. (arg0: torch::jit::Module, arg1: torch_tensorrt._C.ts.CompileSpec) -> torch::jit::Module

Invoked with: <torch.ScriptModule object at 0x7fc2debfd1b0>, <torch_tensorrt._C.ts.CompileSpec object at 0x7fc2d7c86570>
torch_tensorrt failed
Converting method to TensorRT engine...
tensorrt failed
Running Torch for precision: fp16
torch failed
Running Torch-Blade
<=================end================

[mengchengxxx]

pip list
Package Version Location

---

absl-py 1.4.0
antlr4-python3-runtime 4.9.3
attrs 22.2.0
black 23.3.0
cachetools 5.3.0
certifi 2022.12.7
charset-normalizer 3.1.0
click 8.1.3
cloudpickle 2.2.1
contourpy 1.0.7
cPython 0.0.6
cycler 0.11.0
detectron2 0.6 /work/detectron2
distlib 0.3.6
dnspython 2.3.0
exceptiongroup 1.1.1
expecttest 0.1.4
filelock 3.10.7
fonttools 4.39.3
fvcore 0.1.5.post20221221
google-auth 2.17.0
google-auth-oauthlib 0.4.6
grpcio 1.53.0
hydra-core 1.3.2
idna 3.4
importlib-metadata 6.1.0
importlib-resources 5.12.0
iniconfig 2.0.0
iopath 0.1.9
kiwisolver 1.4.4
Markdown 3.4.3
MarkupSafe 2.1.2
matplotlib 3.7.1
mypy-extensions 1.0.0
networkx 3.0
numpy 1.24.2
nvidia-cublas-cu11 2022.4.8
nvidia-cublas-cu117 11.10.1.25
nvidia-cuda-runtime-cu11 2022.4.25
nvidia-cuda-runtime-cu117 11.7.60
nvidia-cudnn-cu11 2022.5.19
nvidia-cudnn-cu116 8.4.0.27
nvidia-pyindex 1.0.9
nvidia-tensorrt 8.4.3.1
oauthlib 3.2.2
omegaconf 2.3.0
onnx 1.12.0
packaging 23.0
pandas 1.5.3
pathspec 0.11.1
Pillow 9.4.0
pip 20.0.2
platformdirs 3.2.0
pluggy 1.0.0
portalocker 2.7.0
protobuf 3.20.1
py-cpuinfo 9.0.0
pyasn1 0.4.8
pyasn1-modules 0.2.8
pybind11 2.6.2
pycocotools 2.0.6
pymongo 4.3.3
pyparsing 3.0.9
pytest 7.2.2
python-dateutil 2.8.2
pytz 2023.2
PyYAML 6.0
requests 2.28.2
requests-oauthlib 1.3.1
rsa 4.9
setuptools 45.2.0
six 1.16.0
tabulate 0.9.0
tensorboard 2.12.0
tensorboard-data-server 0.7.0
tensorboard-plugin-wit 1.8.1
tensorrt 8.2.3.0
termcolor 2.2.0
tomli 2.0.1
torch 1.12.0+cu113
torch-blade 0.2.0+1.12.0.cu113 /work/BladeDISC/pytorch_blade
torch-blade-cpu 0.2.0+1.12.0.cu116
torch-tensorrt 1.2.0
torchvision 0.13.0+cu113
tqdm 4.65.0
typing-extensions 4.5.0
urllib3 1.26.15
virtualenv 20.21.0
Werkzeug 2.2.3
wheel 0.34.2
yacs 0.1.8
zipp 3.15.0