apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 17:11:21 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity

[FDConfig] remove engine client args, use fd_config instead (#5217)

Browse Source 
* [refactor] remove engine client args, use fd_config instead

* [chore] update

* [fix] fix

* [fix] fix

* [chore] rename config to fd_config

* [fix] fix run_batch

* [ci] add ci case for engine client

---------

Co-authored-by: Jiaxin Sui <95567040+plusNew001@users.noreply.github.com>
This commit is contained in:
Yonghua Li
2025-11-28 17:20:54 +08:00
committed by GitHub
parent 73886204d4
commit a535050b11
4 changed files with 70 additions and 1561 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/entrypoints/openai/run_batch.py
+2 -12
View File
@@ -352,22 +352,12 @@ 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)
config = engine_args.create_engine_config(port_availability_check=False)
fd_config = engine_args.create_engine_config(port_availability_check=False)
engine_client = EngineClient(
model_name_or_path=args.model,
tokenizer=args.tokenizer,
max_model_len=args.max_model_len,
tensor_parallel_size=args.tensor_parallel_size,
pid=pid,
port=int(args.engine_worker_queue_port[args.local_data_parallel_id]),
limit_mm_per_prompt=args.limit_mm_per_prompt,
mm_processor_kwargs=args.mm_processor_kwargs,
reasoning_parser=args.reasoning_parser,
data_parallel_size=args.data_parallel_size,
enable_logprob=args.enable_logprob,
fd_config=fd_config,
workers=args.workers,
tool_parser=args.tool_call_parser,
config=config,
)
await engine_client.connection_manager.initialize()