Benchmarks - Revise step time collection in distributed inference benchmark

[yzygitzh]

Description
This commit revises distributed inference benchmark to give a unified step time result by taking maximum step times of different GPUs.

[codecov]

Codecov Report

Merging #524 (8e138f4) into main (51761b3) will increase coverage by 0.00%.
The diff coverage is 100.00%.

@@           Coverage Diff           @@
##             main     #524   +/-   ##
=======================================
  Coverage   87.24%   87.24%           
=======================================
  Files          89       89           
  Lines        5964     5965    +1     
=======================================
+ Hits         5203     5204    +1     
  Misses        761      761           

Flag	Coverage Δ
cpu-python3.6-unit-test	73.48% <50.00%> (+<0.01%)	⬆️
cpu-python3.7-unit-test	73.48% <50.00%> (+<0.01%)	⬆️
cpu-python3.8-unit-test	73.95% <50.00%> (+<0.01%)	⬆️
cuda-unit-test	87.17% <100.00%> (+<0.01%)	⬆️

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

Impacted Files	Coverage Δ
...ench/benchmarks/micro_benchmarks/dist_inference.py	81.14% <100.00%> (+0.10%)	⬆️

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