[Feature] [PD Disaggregation] simplify configuration for pd-disaggregated deployment, and refactor post-init and usage for all ports (#5415)

* [feat] simplify configuration for pd-disaggregated deployment, and refactor post-init and usage for all ports

* [fix] fix some bugs

* [fix] fix rdma port for cache manager/messager

* [fix] temporarily cancel port availability check to see if it can pass ci test

* [feat] simplify args for multi api server

* [fix] fix dp

* [fix] fix port for xpu

* [fix] add tests for ports post processing & fix ci

* [test] fix test_multi_api_server

* [fix] fix rdma_comm_ports args for multi_api_server

* [fix] fix test_common_engine

* [fix] fix test_cache_transfer_manager

* [chore] automatically setting FD_ENABLE_MULTI_API_SERVER

* [fix] avoid api server from creating engine_args twice

* [fix] fix test_run_batch

* [fix] fix test_metrics

* [fix] fix splitwise connector init

* [test] add test_rdma_transfer and test_expert_service

* [fix] fix code syntax

* [fix] fix test_rdma_transfer and build wheel with rdma script
This commit is contained in:
Yonghua Li
2025-12-17 15:50:42 +08:00
committed by GitHub
parent cdc0004894
commit 0c8c6369ed
34 changed files with 1323 additions and 409 deletions
+3 -3
View File
@@ -351,8 +351,8 @@ def create_model_paths(args: Namespace) -> List[ModelPath]:
async def initialize_engine_client(args: Namespace, pid: int) -> EngineClient:
"""Initialize and configure the engine client."""
engine_args = EngineArgs.from_cli_args(args)
fd_config = engine_args.create_engine_config(port_availability_check=False)
engine_args = EngineArgs.from_cli_args(args, skip_port_check=True)
fd_config = engine_args.create_engine_config()
engine_client = EngineClient(
pid=pid,
port=int(args.engine_worker_queue_port[args.local_data_parallel_id]),
@@ -485,7 +485,7 @@ async def main(args: argparse.Namespace):
try:
if args.workers is None:
args.workers = max(min(int(args.max_num_seqs // 32), 8), 1)
console_logger.info(f"Workers: {args.workers}")
args.model = retrive_model_from_server(args.model, args.revision)
if args.tool_parser_plugin: