cpu_thread_num does't work with docker image python:3.9.16-slim-buster

[shao77622]

Environment

FastDeploy version: e.g 0.8.0 or the latest code in develop branch

root@1cfb49fa663e:/home/aiBox# pip list
Package Version

---

anyio 3.6.2
asgiref 3.6.0
certifi 2022.12.7
charset-normalizer 3.1.0
click 8.1.3
faiss-cpu 1.7.3
fastapi 0.93.0
fastdeploy-python 1.0.4
fastdeploy-tools 0.0.5
h11 0.14.0
idna 3.4
numpy 1.24.2
opencv-python 4.7.0.72
Pillow 9.4.0
pip 22.0.4
pydantic 1.10.6
PyYAML 6.0
requests 2.28.2
schedule 1.1.0
setuptools 58.1.0
sniffio 1.3.0
starlette 0.25.0
tqdm 4.65.0
typing_extensions 4.5.0
urllib3 1.26.14
uvicorn 0.16.0
wheel 0.38.4

OS Platform: e.g. Linux x64 / Windows x64 / Mac OSX 12.1(arm or intel)

Linux 1cfb49fa663e 5.10.104-linuxkit #1 SMP Wed Mar 9 19:05:23 UTC 2022 x86_64 GNU/Linux

Hardware: e.g. Nvidia GPU 3080Ti CUDA 11.2 CUDNN 8.3
macbook pro 2019 i9 8 core
Program Language: e.g. Python 3.8

Python 3.9.16 (main, Mar 1 2023, 15:52:45)
[GCC 8.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.

import sys
print(sys.version_info)
sys.version_info(major=3, minor=9, micro=16, releaselevel='final', serial=0)
print(sys.version)
3.9.16 (main, Mar 1 2023, 15:52:45)
[GCC 8.3.0]

Problem description

Please attach the log file if there's problem happend.
fastdeploy infer always use 1 cpu , with max 100%, the option.set_cpu_thread_num() does't work .
But without docker, just run on mac aconda python 3.9 , it works!

[shao77622]

And this is the mac python info below, should be any problems with the deference between GCC 8.3.0 and Clang 14.0.6 ？

Python 3.9.16 (main, Jan 11 2023, 10:02:19)
[Clang 14.0.6 ] :: Anaconda, Inc. on darwin
Type "help", "copyright", "credits" or "license" for more information.

import sys
print(sys.version_info)
sys.version_info(major=3, minor=9, micro=16, releaselevel='final', serial=0)
print(sys.version)
3.9.16 (main, Jan 11 2023, 10:02:19)
[Clang 14.0.6 ]

[shao77622]

OPENVINO does not support multi cpu, but ort backend works.

[jiangjiajun]

While inference with OpenVINO, the cpu_thread_num doesn't mean that the engine will use the setting number of threads to inference, it means the number of threads it used will not exceed the cpu_thread_num