Feature/SGlang support

[XkunW]

PR Type

[Feature]

Short Description

• Abstract inference engine
• Add SGlang as alternative inference engine to vLLM
• Update default model and environment config formats
• Update model types to be dynamic

[codecov-commenter]

Codecov Report

❌ Patch coverage is 96.77419% with 5 lines in your changes missing coverage. Please review.
✅ Project coverage is 91.32%. Comparing base (e8f0788) to head (d75bfe7).

Files with missing lines	Patch %	Lines
vec_inf/client/_slurm_script_generator.py	90.32%	3 Missing ⚠️
vec_inf/cli/_cli.py	75.00%	1 Missing ⚠️
vec_inf/client/_utils.py	83.33%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #164      +/-   ##
==========================================
+ Coverage   90.83%   91.32%   +0.49%     
==========================================
  Files          14       14              
  Lines        1342     1430      +88     
==========================================
+ Hits         1219     1306      +87     
- Misses        123      124       +1     

Files with missing lines	Coverage Δ
vec_inf/cli/_helper.py	95.47% <100.00%> (+0.16%)	⬆️
vec_inf/cli/_vars.py	100.00% <100.00%> (ø)
vec_inf/client/_client_vars.py	100.00% <100.00%> (ø)
vec_inf/client/_helper.py	93.26% <100.00%> (+0.65%)	⬆️
vec_inf/client/_slurm_templates.py	100.00% <100.00%> (ø)
vec_inf/client/_slurm_vars.py	80.43% <100.00%> (+1.36%)	⬆️
vec_inf/client/config.py	100.00% <100.00%> (ø)
vec_inf/client/models.py	100.00% <100.00%> (ø)
vec_inf/cli/_cli.py	88.00% <75.00%> (-0.31%)	⬇️
vec_inf/client/_utils.py	80.98% <83.33%> (+2.09%)	⬆️
... and 1 more

🚀 New features to boost your workflow:

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