feat: add ranker endpoint for all backends

[numb3r3]

TODO:

• explain how to config logit_scale
  • from pre-trained model (same as torch implementation)
  • could be a static global variable or a parameter (this PR in onnx and tensorrt)

[codecov]

Codecov Report

Merging #707 (d2dda01) into main (618dbdb) will increase coverage by 0.76%.
The diff coverage is 92.77%.

@@            Coverage Diff             @@
##             main     #707      +/-   ##
==========================================
+ Coverage   80.27%   81.03%   +0.76%     
==========================================
  Files          16       16              
  Lines        1100     1176      +76     
==========================================
+ Hits          883      953      +70     
- Misses        217      223       +6     

Flag	Coverage Δ
cas	81.03% <92.77%> (+0.76%)	⬆️

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

Impacted Files	Coverage Δ
server/clip_server/executors/clip_trt.py	95.77% <92.10%> (-4.23%)	⬇️
server/clip_server/executors/clip_onnx.py	86.81% <93.02%> (+5.18%)	⬆️
server/clip_server/executors/clip_torch.py	87.01% <100.00%> (-0.33%)	⬇️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 618dbdb...d2dda01. Read the comment docs.