concatenate sampler states from chains

[penelopeysm]

Closes #487

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 86.03%. Comparing base (a45c09e) to head (cc22cbd).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #488      +/-   ##
==========================================
+ Coverage   86.01%   86.03%   +0.02%     
==========================================
  Files          20       20              
  Lines        1144     1146       +2     
==========================================
+ Hits          984      986       +2     
  Misses        160      160              

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

🚀 New features to boost your workflow:

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

[github-actions]

MCMCChains.jl documentation for PR #488 is available at:
https://TuringLang.github.io/MCMCChains.jl/previews/PR488/

[penelopeysm]

@joelkandiah Would you be able to test if this PR works correctly? I think the following workflow should be fine with this PR:

using Turing, Test # and anything else you need

chn = sample(model, spl, MCMCThreads(), N1, M; save_state=true)

# do some sanity checks
@test chn.info.samplerstate isa AbstractVector
@test length(chn.info.samplerstate) == M

chn2 = sample(model, spl, MCMCThreads(), N2, M; initial_state=chn.info.samplerstate)

[joelkandiah]

Ran the checks and a few others and am happy this is working as intended!