feat: add faster tokenizer

[OrangeSodahub]

Add a faster tokenizer (original from rust-tokenizer).

[github-actions[bot]]

This PR exceeds the recommended size of 1000 lines. Please make sure you are NOT addressing multiple issues with one PR. Note this PR might be rejected due to its size.

[codecov[bot]]

Codecov Report

Merging #868 (37cf884) into main (67f551c) will decrease coverage by 3.42%. The diff coverage is 21.95%.

@@            Coverage Diff             @@
##             main     #868      +/-   ##
==========================================
- Coverage   80.28%   76.85%   -3.43%     
==========================================
  Files          22       23       +1     
  Lines        1633     1672      +39     
==========================================
- Hits         1311     1285      -26     
- Misses        322      387      +65     

Flag	Coverage Δ
cas	76.85% <21.95%> (-3.43%)	: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/fast_tokenizer.py	11.42% <11.42%> (ø)
server/clip_server/model/tokenization.py	86.48% <83.33%> (-1.40%)	:arrow_down:
server/clip_server/model/trt_utils.py	56.04% <0.00%> (-27.48%)	:arrow_down:
server/clip_server/model/clip_trt.py	69.38% <0.00%> (-16.33%)	:arrow_down:

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

[ZiniuYu]

牛啊

[numb3r3]

Since rust-tokenizer is not pip installable. I would close this PR atm.