[RL] R3 Support RDMA Store

[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)

Performance comparison between RoutingStoreLocal and RoutingStoreRDMA:

1. paddle.load overhead:
   Number of successfully `get` files: 37/37
   Mean overhead: 0.0395 s
   Min overhead: 0.0127 s
   Max overhead: 0.1590 s
   Total overhead: 1.4610 s

2. paddle.save overhead:
   Number of successfully `save` files: 37/37
   Mean overhead:  0.0872 s
   Min overhead: 0.0692 s
   Max overhead: 0.1226 s
   Total overhead: 3.2273 s

3. p2pstore.put overhead:
   Number of successfully `put` files: 37/37
   Mean overhead: 0.0073 s
   Min overhead: 0.0063 s
   Max overhead: 0.0076 s
   Total overhead: 0.2691 s

4. p2pstore.get overhead:
   Number of successfully `get` files: 37/37
   Mean overhead: 0.0027 s
   Min overhead: 0.0027 s
   Max overhead: 0.0029 s
   Total overhead: 0.1008 s

release/2.4 PR: #5468
exp_0908 PR: #5454

Modifications

Add RoutingStoreRDMA, using P2P communication to transmit routing.

• Routing will be stored in the WorkerProcess process where the RoutingStoreRDMA is located and will not be actively released.
• Thep2pstore dependency library and 'RoutingStoreRDMA' can only be used in RLHF of PaddlePaddle

Usage or Command

Add new parameters for RoutingReplayConfig:

--routing-replay-config '{"enable_routing_replay":true, "routing_store_type":"rdma", "rdma_store_server":"zmq://x.x.x.x:5765,x.x.x.x:5766"}' 

Accuracy Tests

None

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 32.43243% with 25 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@c9b47f9). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...model_executor/layers/moe/routing_indices_cache.py	28.12%	23 Missing ⚠️
fastdeploy/worker/gpu_model_runner.py	0.00%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5467   +/-   ##
==========================================
  Coverage           ?   61.79%           
==========================================
  Files              ?      329           
  Lines              ?    41193           
  Branches           ?     6276           
==========================================
  Hits               ?    25457           
  Misses             ?    13820           
  Partials           ?     1916           

Flag	Coverage Δ
GPU	61.79% <32.43%> (?)

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.

[Jiang-Jia-Jun]

LGTM for skip coverage