fix: install pytorch cu116 for server docker image

[ZiniuYu]

This PR fixes the error in linked issue

[jemmyshin]

please rebuild the image and reply to the communities.

[codecov[bot]]

Codecov Report

Merging #882 (a3d8796) into main (0b293ec) will decrease coverage by 11.27%. The diff coverage is 100.00%.

@@             Coverage Diff             @@
##             main     #882       +/-   ##
===========================================
- Coverage   83.06%   71.78%   -11.28%     
===========================================
  Files          22       22               
  Lines        1529     1531        +2     
===========================================
- Hits         1270     1099      -171     
- Misses        259      432      +173     

Flag	Coverage Δ
cas	71.78% <100.00%> (-11.28%)	:arrow_down:

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
server/clip_server/model/model.py	75.37% <100.00%> (+0.18%)	:arrow_up:
server/clip_server/executors/clip_tensorrt.py	0.00% <0.00%> (-94.60%)	:arrow_down:
server/clip_server/model/clip_trt.py	0.00% <0.00%> (-85.72%)	:arrow_down:
server/clip_server/model/trt_utils.py	0.00% <0.00%> (-83.52%)	:arrow_down:
server/clip_server/executors/clip_onnx.py	87.91% <0.00%> (+1.09%)	:arrow_up:
server/clip_server/model/clip_onnx.py	87.30% <0.00%> (+22.22%)	:arrow_up:

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

[numb3r3]

@ZiniuYu Does the hub executor also suffer from this issue?

[ZiniuYu]

@ZiniuYu Does the hub executor also suffer from this issue?

I just tested both Torch and ONNX executors, they are all fine

[numb3r3]

I just tested both Torch and ONNX executors, they are all fine

Then, I doubled if this issue comes from cuda? And I would not recommend pinning the cuda version. Our work should work on all stable cuda versions.

[numb3r3]

So, please try to make it work with cuda-11.6.0, rather than freeze the cuda version.