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

[BugFix] Fix the abnormal memory usage caused by shape errors in the triton moe backend (#4026)

Browse Source 
* fix device_id to in

* fix triton_moe bug
This commit is contained in:
Yuanle Liu
2025-09-10 11:05:54 +08:00
committed by GitHub
parent dbab579299
commit c3b2a60fb8
4 changed files with 12 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
fastdeploy/utils.py
View File

@@ -516,13 +516,13 @@ def print_gpu_memory_use(gpu_id: int, title: str) -> None:
print(
f"\n{title}:",
f"\n\tDevice Total memory: {meminfo.total}",
f"\n\tDevice Used memory: {meminfo.used}",
f"\n\tDevice Free memory: {meminfo.free}",
f"\n\tPaddle max memory Reserved: {paddle_max_reserved}",
f"\n\tPaddle max memory Allocated: {paddle_max_allocated}",
f"\n\tPaddle memory Reserved: {paddle_reserved}",
f"\n\tPaddle memory Allocated: {paddle_allocated}",
f"\n\tDevice Total memory(GiB): {meminfo.total / 1024.0 / 1024.0 / 1024.0}",
f"\n\tDevice Used memory(GiB): {meminfo.used / 1024.0 / 1024.0 / 1024.0}",
f"\n\tDevice Free memory(GiB): {meminfo.free / 1024.0 / 1024.0 / 1024.0}",
f"\n\tPaddle max memory Reserved(GiB): {paddle_max_reserved / 1024.0 / 1024.0 / 1024.0}",
f"\n\tPaddle max memory Allocated(GiB): {paddle_max_allocated / 1024.0 / 1024.0 / 1024.0}",
f"\n\tPaddle memory Reserved(GiB): {paddle_reserved / 1024.0 / 1024.0 / 1024.0}",
f"\n\tPaddle memory Allocated(GiB): {paddle_allocated / 1024.0 / 1024.0 / 1024.0}",
)