本地部署UDPipe 2.10服务器遇TensorFlow加载问题求指导

我正尝试在本地机器上部署UDPipe 2.10版本服务器，已按照其GitHub仓库中的要求安装了依赖。

运行udpipe2_server.py时出现以下错误：

2023-12-26 11:41:28.060713: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-12-26 11:41:28.152568: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2023-12-26 11:41:28.152588: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2023-12-26 11:41:28.174947: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2023-12-26 11:41:28.594525: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2023-12-26 11:41:28.594616: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2023-12-26 11:41:28.594625: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
Traceback (most recent call last):
  File "/home/sumanth/sumanth.k/udpipe/udpipe2_server.py", line 26, in <module>
    import udpipe2
  File "/home/sumanth/sumanth.k/udpipe/udpipe2.py", line 19, in <module>
    import tensorflow as tf
  File "/home/sumanth/sumanth.k/udpipe/venv/lib/python3.10/site-packages/tensorflow/__init__.py", line 469, in <module>
    _keras._load()

我尝试安装wembedding_service后仍出现错误：

2023-12-26 11:45:15.604154: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-12-26 11:45:15.695350: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2023-12-26 11:45:15.695370: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2023-12-26 11:45:15.717002: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2023-12-26 11:45:16.149980: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2023-12-26 11:45:16.150044: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2023-12-26 11:45:16.150053: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
Traceback (most recent call last):
  File "/home/sumanth/sumanth.k/udpipe/wembedding_service/./start_wembeddings_server.py", line 58, in <module>
    server = wembeddings_server.WEmbeddingsServer(args.port, args.dtype, wembeddings_lambda)
  File "/home/sumanth/sumanth.k/udpipe/wembedding_service/wembeddings/wembeddings_server.py", line 102, in __init__
    self._wembeddings = wembeddings_lambda()
  File "/home/sumanth/sumanth.k/udpipe/wembedding_service/./start_wembeddings_server.py", line 50, in <lambda>
    wembeddings_lambda = lambda: wembeddings.WEmbeddings(threads=args.threads, preload_models=args.preload_models)
  File "/home/sumanth/sumanth.k/udpipe/wembedding_service/wembeddings/wembeddings.py", line 77, in __init__
    import tensorflow as tf
  File "/home/sumanth/sumanth.k/udpipe/venv/lib/python3.10/site-packages/tensorflow/__init__.py", line 469, in <module>
    _keras._load()
  File "/home/sumanth/sumanth.k/udpipe/venv/lib/python3.10/site-packages/tensorflow/python/util/lazy_loader.py", line 41, in _load
    module = importlib.import_module(self.__name__)

恳请各位指导我完成UDPipe在本地机器上的部署。

内容的提问来源于stack exchange，提问作者SUMANTH K