Allow generation of ParamsWithStats from FastLDF plus parameters, and also bundle_samples

[penelopeysm]

This has no real impact on DynamicPPL, but using this in Turing should lead to some nice speedups because this:

1. is faster to evaluate than regular unflatten + evaluate!!;
2. avoids deepcopying VarInfo.

Closes #1119.

Since the intention of this is to replace Turing.Inference.Transition with ParamsWithStats, I also added the necessary AbstractMCMC.bundle_samples method here. MCMCChainsExt is the natural place for it to live (it could be defined in Turing, but that would be piracy).

[github-actions]

Benchmark Report for Commit 2fad97b

Computer Information

Julia Version 1.11.7
Commit f2b3dbda30a (2025-09-08 12:10 UTC)
Build Info:
  Official https://julialang.org/ release
Platform Info:
  OS: Linux (x86_64-linux-gnu)
  CPU: 4 × Intel(R) Xeon(R) Platinum 8370C CPU @ 2.80GHz
  WORD_SIZE: 64
  LLVM: libLLVM-16.0.6 (ORCJIT, icelake-server)
Threads: 1 default, 0 interactive, 1 GC (on 4 virtual cores)

Benchmark Results

┌───────────────────────┬───────┬─────────────┬───────────────────┬────────┬────────────────┬─────────────────┐
│                 Model │   Dim │  AD Backend │           VarInfo │ Linked │ t(eval)/t(ref) │ t(grad)/t(eval) │
├───────────────────────┼───────┼─────────────┼───────────────────┼────────┼────────────────┼─────────────────┤
│ Simple assume observe │     1 │ forwarddiff │             typed │  false │            6.2 │             1.9 │
│           Smorgasbord │   201 │ forwarddiff │             typed │  false │          746.6 │            42.0 │
│           Smorgasbord │   201 │ forwarddiff │ simple_namedtuple │   true │          407.7 │            58.1 │
│           Smorgasbord │   201 │ forwarddiff │           untyped │   true │          794.6 │            40.7 │
│           Smorgasbord │   201 │ forwarddiff │       simple_dict │   true │         6633.4 │            26.6 │
│           Smorgasbord │   201 │ forwarddiff │      typed_vector │   true │          752.9 │            43.3 │
│           Smorgasbord │   201 │ forwarddiff │    untyped_vector │   true │          748.1 │            39.6 │
│           Smorgasbord │   201 │ reversediff │             typed │   true │          843.0 │            48.6 │
│           Smorgasbord │   201 │    mooncake │             typed │   true │          716.1 │             5.5 │
│           Smorgasbord │   201 │      enzyme │             typed │   true │          845.6 │             4.3 │
│    Loop univariate 1k │  1000 │    mooncake │             typed │   true │         3405.3 │             6.6 │
│       Multivariate 1k │  1000 │    mooncake │             typed │   true │         1178.3 │             7.2 │
│   Loop univariate 10k │ 10000 │    mooncake │             typed │   true │        36183.5 │             6.2 │
│      Multivariate 10k │ 10000 │    mooncake │             typed │   true │        10837.3 │             7.9 │
│               Dynamic │    10 │    mooncake │             typed │   true │          129.5 │             8.1 │
│              Submodel │     1 │    mooncake │             typed │   true │            8.4 │             6.1 │
│                   LDA │    12 │ reversediff │             typed │   true │          854.6 │             2.2 │
└───────────────────────┴───────┴─────────────┴───────────────────┴────────┴────────────────┴─────────────────┘

[github-actions]

DynamicPPL.jl documentation for PR #1129 is available at:
https://TuringLang.github.io/DynamicPPL.jl/previews/PR1129/

[codecov]

Codecov Report

❌ Patch coverage is 72.72727% with 9 lines in your changes missing coverage. Please review.
✅ Project coverage is 81.53%. Comparing base (ce80713) to head (2fad97b).

Files with missing lines	Patch %	Lines
ext/DynamicPPLMCMCChainsExt.jl	0.00%	9 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff              @@
##           breaking    #1129      +/-   ##
============================================
- Coverage     81.72%   81.53%   -0.19%     
============================================
  Files            42       42              
  Lines          3928     3953      +25     
============================================
+ Hits           3210     3223      +13     
- Misses          718      730      +12     

☔ 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.