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

[Feature] support custom all-reduce (#2758)

Browse Source 
* [Feature] support custom all-reduce

* add vllm adapted
This commit is contained in:
zhink
2025-07-09 16:00:27 +08:00
committed by GitHub
parent be21ef5047
commit b89180f1cd
16 changed files with 1194 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
fastdeploy/worker/gpu_worker.py
View File

@@ -60,6 +60,9 @@ 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
use_custom_allreduce()
else:
raise RuntimeError(
f"Not support device type: {self.device_config.device}")