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

custom all reduce support cuda graph (#2938)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* Support enabling cuda graph and custom all reduce at the same time, and fix the overwritten custom all reduce flag

* rename communication_op to communication
This commit is contained in:
zhink
2025-07-21 22:52:03 +08:00
committed by GitHub
parent ff4569f135
commit 0262ef7eb3
21 changed files with 88 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/worker/gpu_worker.py
View File

@@ -62,7 +62,7 @@ class GpuWorker(WorkerBase):
gc.collect()
paddle.device.cuda.empty_cache()
if self.parallel_config.enable_custom_all_reduce:
from fastdeploy.distributed.communication_op import use_custom_allreduce
from fastdeploy.distributed.communication import use_custom_allreduce
use_custom_allreduce()
else: