apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Modified to support custom all reduce by default (#3538)

Browse Source
This commit is contained in:
zhink
2025-08-22 16:59:05 +08:00
committed by GitHub
parent 27666ee586
commit df7c31012b
15 changed files with 18 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/worker/gpu_worker.py
View File

@@ -69,7 +69,7 @@ class GpuWorker(WorkerBase):
gc.collect()
paddle.device.cuda.empty_cache()
if (
self.parallel_config.enable_custom_all_reduce
not self.parallel_config.disable_custom_all_reduce
and self.parallel_config.tensor_parallel_size > 1
and paddle.is_compiled_with_cuda()
):

2
fastdeploy/worker/worker_process.py
View File

@@ -516,7 +516,7 @@ def parse_args():
help="enable prefix cache",
)
parser.add_argument(
"--enable_custom_all_reduce",
"--disable_custom_all_reduce",
action="store_true",
help="enable custom all-reduce",
)