DOC: LLM inference

[UranusSeven]

What do these changes do?

Add a tutorial that do LLM inference with Xoscar on both CPU and GPU.

Related issue number

Check code requirements

• [x] tests added / passed (if needed)
• [x] Ensure all linting tests pass

[codecov[bot]]

Codecov Report

Merging #30 (c62e82c) into main (a6909c2) will decrease coverage by 0.35%. The diff coverage is n/a.

@@            Coverage Diff             @@
##             main      #30      +/-   ##
==========================================
- Coverage   91.65%   91.30%   -0.35%     
==========================================
  Files          42       42              
  Lines        3187     3187              
  Branches      638      638              
==========================================
- Hits         2921     2910      -11     
- Misses        194      204      +10     
- Partials       72       73       +1     

Flag	Coverage Δ
unittests	91.15% <ø> (-0.35%)	:arrow_down:

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

see 3 files with indirect coverage changes