Refactor of Sequential Monte Carlo internals

[ciguaran]

This is my first PR ever to Pymc.
There should not be any breaking changes. This PR modularizes a little bit SMC internals.
This is an initial refactor, that adds documentation and makes it easier for a new reader to find where the actual SMC sampling happens, vs what checks/stats are generated.
@ricardoV94

[codecov]

Codecov Report

Merging #5281 (72834d5) into main (9d4691c) will increase coverage by 0.01%.
The diff coverage is 66.66%.

@@            Coverage Diff             @@
##             main    #5281      +/-   ##
==========================================
+ Coverage   78.98%   78.99%   +0.01%     
==========================================
  Files          88       87       -1     
  Lines       14273    14364      +91     
==========================================
+ Hits        11273    11347      +74     
- Misses       3000     3017      +17     

Impacted Files	Coverage Δ
pymc/smc/smc.py	97.89% <50.00%> (-0.41%)	⬇️
pymc/smc/sample_smc.py	83.22% <67.56%> (-0.12%)	⬇️
pymc/backends/ndarray.py	79.64% <0.00%> (-9.74%)	⬇️
pymc/bart/utils.py	82.60% <0.00%> (-5.92%)	⬇️
pymc/backends/report.py	89.51% <0.00%> (-2.10%)	⬇️
pymc/distributions/dist_math.py	86.78% <0.00%> (-0.92%)	⬇️
pymc/sampling.py	86.23% <0.00%> (-0.57%)	⬇️
pymc/backends/arviz.py	89.12% <0.00%> (-0.44%)	⬇️
pymc/gp/gp.py	93.18% <0.00%> (-0.43%)	⬇️
pymc/model.py	82.99% <0.00%> (-0.32%)	⬇️
... and 18 more

[ricardoV94]

Thanks @ciguaran