apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 16:22:57 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[feature]2.2 custom_allreduce support cudagraph recapture (#4307)

Browse Source 
* custom_allreduce support cudagraph recapture

* delete code

* add shut_down/restart default group
This commit is contained in:
chen
2025-09-29 18:14:21 +08:00
committed by GitHub
parent 9cc2c99539
commit 63a03ee152
7 changed files with 31 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/model_executor/graph_optimization/cudagraph_piecewise_backend.py
View File

@@ -23,7 +23,10 @@ import paddle.nn.layer
from paddle.device.cuda import graphs
from fastdeploy.config import FDConfig
from fastdeploy.distributed.communication import capture_custom_allreduce
from fastdeploy.distributed.communication import (
capture_custom_allreduce,
custom_ar_clear_ipc_handles,
)
from fastdeploy.utils import get_logger
logger = get_logger("cudagrpah_piecewise_backend", "cudagraph_piecewise_backend.log")
@@ -208,6 +211,7 @@ class CudaGraphPiecewiseBackend:
def clear_graph(self):
""" """
# Clear graphs
custom_ar_clear_ipc_handles()
for id, entry in self.concrete_size_entries.items():
if entry.cuda_graph:
del entry.cuda_graph