Support for additional vLLM server arguments

[kohankhaki]

PR Type

Feature

Short Description

Adding support for additional vLLM server arguments and improving the handling of these arguments throughout the codebase.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 54.34783% with 21 lines in your changes missing coverage. Please review.

Project coverage is 80.71%. Comparing base (9ffac32) to head (c455b4d).

Files with missing lines	Patch %	Lines
vec_inf/cli/_cli.py	48.14%	14 Missing ⚠️
vec_inf/client/_slurm_script_generator.py	37.50%	5 Missing ⚠️
vec_inf/cli/_helper.py	60.00%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #89      +/-   ##
==========================================
- Coverage   82.39%   80.71%   -1.69%     
==========================================
  Files          12       12              
  Lines         835      871      +36     
==========================================
+ Hits          688      703      +15     
- Misses        147      168      +21     

Files with missing lines	Coverage Δ
vec_inf/client/_helper.py	79.91% <100.00%> (+0.17%)	⬆️
vec_inf/client/_models.py	100.00% <100.00%> (ø)
vec_inf/cli/_helper.py	76.69% <60.00%> (-0.66%)	⬇️
vec_inf/client/_slurm_script_generator.py	71.25% <37.50%> (-4.10%)	⬇️
vec_inf/cli/_cli.py	70.71% <48.14%> (-6.79%)	⬇️

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.