feat: add metrics endpoint to inference

[ishaansehgal99]

Adds simple GET /metrics endpoint

i.e. wrt falcon-7b-instruct
{"gpu_info":[{"id":0,"name":"Tesla V100-PCIE-16GB","load":"0.00%","temperature":"30.0 C","memory":{"used":"7.08 GB","total":"16.00 GB"}},{"id":1,"name":"Tesla V100-PCIE-16GB","load":"0.00%","temperature":"29.0 C","memory":{"used":"6.53 GB","total":"16.00 GB"}}]}

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (7856b76) 65.81% compared to head (110b61e) 65.81%.
Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #207   +/-   ##
=======================================
  Coverage   65.81%   65.81%           
=======================================
  Files          14       14           
  Lines        1366     1366           
=======================================
  Hits          899      899           
  Misses        429      429           
  Partials       38       38           

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

[ishaansehgal99]

Included in #216 and #217