apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[FDConfig]Remove splitwise_role and engine_worker_queue_port in FDConfig (#4147)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* remove splitwise_role and engine_worker_queue_port

* fix xpu

* fix xpu

* fix xpu

* fix unittest

* resolve conflct
This commit is contained in:
YuanRisheng
2025-09-19 17:01:52 +08:00
committed by GitHub
parent ee9d8a840a
commit 24180fba0a
23 changed files with 129 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
fastdeploy/engine/args_utils.py
View File

@@ -1019,6 +1019,11 @@ class EngineArgs:
else:
self.max_num_batched_tokens = self.max_model_len
if isinstance(self.engine_worker_queue_port, int):
self.engine_worker_queue_port = str(self.engine_worker_queue_port)
if isinstance(self.engine_worker_queue_port, str):
self.engine_worker_queue_port = self.engine_worker_queue_port.split(",")
all_dict = asdict(self)
all_dict["model_cfg"] = model_cfg
cache_cfg = CacheConfig(all_dict)
@@ -1032,11 +1037,6 @@ class EngineArgs:
early_stop_cfg = self.create_early_stop_config()
early_stop_cfg.update_enable_early_stop(self.enable_early_stop)
if isinstance(self.engine_worker_queue_port, int):
self.engine_worker_queue_port = str(self.engine_worker_queue_port)
if isinstance(self.engine_worker_queue_port, str):
self.engine_worker_queue_port = self.engine_worker_queue_port.split(",")
assert is_port_available(
"0.0.0.0", int(self.engine_worker_queue_port[parallel_cfg.local_data_parallel_id])
), f"The parameter `engine_worker_queue_port`:{self.engine_worker_queue_port} is already in use."
@@ -1052,12 +1052,10 @@ class EngineArgs:
speculative_config=speculative_cfg,
ips=self.ips,
use_warmup=self.use_warmup,
engine_worker_queue_port=self.engine_worker_queue_port,
limit_mm_per_prompt=self.limit_mm_per_prompt,
mm_processor_kwargs=self.mm_processor_kwargs,
reasoning_parser=self.reasoning_parser,
tool_parser=self.tool_call_parser,
splitwise_role=self.splitwise_role,
innode_prefill_ports=self.innode_prefill_ports,
max_num_partial_prefills=self.max_num_partial_prefills,
max_long_partial_prefills=self.max_long_partial_prefills,