register_jit_hooks: Remove confusing error message

[HolyWu]

Description

import torch
import torch_tensorrt

model = torch.nn.ReLU().eval().cuda()

inputs = [torch.randn(1, 3, 224, 224, device="cuda")]

trt_model = torch_tensorrt.compile(
    model,
    ir="dynamo",
    inputs=inputs,
    enabled_precisions={torch.float},
    min_block_size=1,
    make_refitable=False,
    cache_built_engines=False,
    reuse_cached_engines=False,
)

torch_tensorrt.save(trt_model, "trt.ts", output_format="torchscript", inputs=inputs)
loaded_model = torch_tensorrt.load("trt.ts")

holywu@HOLYWU:~$ python3 test.py
Unable to import quantization op. Please install modelopt library (https://github.com/NVIDIA/TensorRT-Model-Optimizer?tab=readme-ov-file#installation) to add support for compiling quantized models
WARNING:torch_tensorrt.dynamo.utils:Could not detect the device on which the model exists. Assuming the model is on CPU
WARNING: [Torch-TensorRT] - Using default stream in enqueueV3() may lead to performance issues due to additional calls to cudaStreamSynchronize() by TensorRT to ensure correct synchronization. Please use non-default stream instead.
ERROR: [Torch-TensorRT] - linux_x86_64
holywu@HOLYWU:~$