[Serve] Support xPyD Disaggregation in multiple nodes

[cyber-pioneer]

Description: Multi-node Prefill/Decode Disaggregated Deployment with FlagCX

This PR implements support for multi-node disaggregated deployment of prefill and decode stages using xPyD Disaggregation:

• Schedule strategies of PD instances currently support: robin, random. default is robin.
• It introduces a new communication backend based on FlagCX. Merge FlagCX Adapter.
• KV cache transfer is enabled via p2pConnector in vLLM.

---

How to Use

Step 1: Install FlagCX

Step 2: Install the vLLM version from FlagScale

Step 3: Define your config files under ./examples/qwen/conf

Step 4: Launch the distributed deployment

python run.py --config-path ./examples/qwen/conf --config-name config_qwen2.5_7b_disagg_xpyd action=run

Step 5: Send requests to the deployed service

curl -X POST -s http://localhost:10001/v1/completions \
-H "Content-Type: application/json" \
-d '{
  "model": "/models/Qwen2.5-7B-Instruct",
  "prompt": "Introduce Bruce Lee in details",
  "max_tokens": 100,
  "temperature": 0,
  "stream": true
}'

[aoyulong]

LGTM