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

fix num_blocks_local when small size model in TP2 running mode (#2792)

Browse Source
This commit is contained in:
gaoziyuan
2025-07-12 12:50:48 +08:00
committed by GitHub
parent 749b2e9c89
commit e9e8443ea8
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/worker/worker_process.py
View File

@@ -360,11 +360,11 @@ class PaddleDisWorkerProc():
model_block_memory_used)
# NOTE(liuzichang): Too many block will lead to illegal memory access
# We will develop dynamic limits in future.
if num_blocks_local > 20000:
if num_blocks_local > 40000:
logger.info(
f"------- Reset num_blocks_local {num_blocks_local} to 20000"
f"------- Reset num_blocks_local {num_blocks_local} to 40000"
)
num_blocks_local = min(20000, num_blocks_local)
num_blocks_local = min(40000, num_blocks_local)
logger.info(
f"------- model_block_memory_used:{model_block_memory_used} --------"
)