apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 17:17:14 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Cherry-Pick] Launch expert_service before kv_cache initialization in worker_process (#3558)

Browse Source 
* launch expert_service before kv_cache initialization

* update code

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
Zero Rains
2025-08-23 13:08:34 +08:00
committed by GitHub
parent e8af92aab7
commit f8d3255520
3 changed files with 149 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
fastdeploy/worker/worker_process.py
View File

@@ -458,6 +458,17 @@ class PaddleDisWorkerProc:
def load_model(self) -> None:
"""Load weights and create model"""
self.worker.load_model()
loaded_model_signal_data = np.zeros(shape=[1], dtype=np.int32)
self.loaded_model_signal = IPCSignal(
name="loaded_model_signal",
array=loaded_model_signal_data,
dtype=np.int32,
suffix=self.parallel_config.engine_pid,
create=False,
)
if self.ranks > 1:
paddle.distributed.barrier()
self.loaded_model_signal.value[0] = 1
def parse_args():