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

Print KV Cache available memory and block memory usage in GB format (#4148)

Browse Source
This commit is contained in:
qw86972190
2025-09-17 20:01:55 +08:00
committed by GitHub
parent 2adca04f1f
commit b52971749c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/worker/worker_process.py
View File

@@ -382,7 +382,7 @@ class PaddleDisWorkerProc:
if num_blocks_local > 40000: if num_blocks_local > 40000:
logger.info(f"------- Reset num_blocks_local {num_blocks_local} to 40000") logger.info(f"------- Reset num_blocks_local {num_blocks_local} to 40000")
num_blocks_local = min(40000, num_blocks_local) num_blocks_local = min(40000, num_blocks_local)
logger.info(f"------- model_block_memory_used:{model_block_memory_used} --------") logger.info(f"------- model_block_memory_used:{model_block_memory_used / 1024**3} GB --------")
logger.info(f"------- num_blocks_local:{num_blocks_local} --------") logger.info(f"------- num_blocks_local:{num_blocks_local} --------")
if num_blocks_local <= 0: if num_blocks_local <= 0: