mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 17:11:21 +08:00
[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:
@@ -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:
|
||||
|
||||
Reference in New Issue
Block a user