feat(scripts): clean LLM latency benchmark

[frgfm]

This PR introduces the following modifications:

• add docker options to run the benchmark
• update the bechmark results
• update the README and add a dedicated readme for benchmarks

Closes #130

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 83.97%. Comparing base (78f74cc) to head (76aca8d).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #132   +/-   ##
=======================================
  Coverage   83.97%   83.97%           
=======================================
  Files          29       29           
  Lines         911      911           
=======================================
  Hits          765      765           
  Misses        146      146           

Flag	Coverage Δ
unittests	83.97% <ø> (ø)

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

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.