[RL] Support Rollout Routing Replay

[gongshaotian]

Motivation

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

In RL training tasks, we have enabled recording of routing information during the inference process and directly utilized the experts selected during inference in the training process to alleviate the consistency issue between training and inference.

0908 branch: #5166

Modifications

Add RoutingReplayManager and RoutingStore class to support routing replay

• RoutingStore: The client used for interacting with Routing Store has two routing storage modes based on File System and RDMA(WIP).
• RoutingReplayManager: Implement request level routing table management within FastDeploy.

Model support:

• EB5
• EB4.5
• GLM

Usage or Command

Add a startup switch for route replay：

    --routing-replay-config '{"enable_routing_replay":true, "routing_store_type":"local", "local_store_dir":"xxx/routing_replay_output"}'

Accuracy Tests

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[paddle-bot]

Thanks for your contribution!

[codecov-commenter]

Codecov Report

❌ Patch coverage is 34.40367% with 143 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@84e2f6a). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...model_executor/layers/moe/routing_indices_cache.py	25.69%	107 Missing ⚠️
..._executor/layers/moe/fused_moe_deepgemm_backend.py	0.00%	7 Missing ⚠️
...l_executor/layers/moe/fused_moe_cutlass_backend.py	14.28%	5 Missing and 1 partial ⚠️
...el_executor/layers/moe/fused_moe_triton_backend.py	14.28%	5 Missing and 1 partial ⚠️
...del_executor/layers/moe/fused_moe_wint2_backend.py	0.00%	5 Missing ⚠️
fastdeploy/model_executor/layers/moe/moe.py	71.42%	3 Missing and 1 partial ⚠️
fastdeploy/engine/args_utils.py	70.00%	2 Missing and 1 partial ⚠️
...el_executor/layers/moe/fused_moe_marlin_backend.py	0.00%	3 Missing ⚠️
...odel_executor/layers/moe/fused_moe_backend_base.py	50.00%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5321   +/-   ##
==========================================
  Coverage           ?   59.13%           
==========================================
  Files              ?      325           
  Lines              ?    39911           
  Branches           ?     6004           
==========================================
  Hits               ?    23602           
  Misses             ?    14422           
  Partials           ?     1887           

Flag	Coverage Δ
GPU	59.13% <34.40%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ 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.