apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Other] Use symbolic link pointed to TensorRT library (#1461)

Browse Source 
* Add force rpath

* update to dev-6

* remove force-rpath

* remove nvinfer so

* Add symbol link creation when import fastdeploy first

* Add dst

* update symbol link creation

* Add logging

* logging -> logger

* update tips

* Set logging level

* Add --force-rpath
This commit is contained in:
Jack Zhou
2023-03-10 09:09:04 +08:00
committed by GitHub
parent a14480ae2b
commit f7ef464412
5 changed files with 36 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/patch_paddle_inference.py
View File

@@ -30,8 +30,8 @@ def process_paddle_inference(paddle_inference_so_file):
]
patchelf_exe = os.getenv("PATCHELF_EXE", "patchelf")
command = "{} --set-rpath '{}' {}".format(patchelf_exe, ":".join(rpaths),
paddle_inference_so_file)
command = "{} --force-rpath --set-rpath '{}' {}".format(
patchelf_exe, ":".join(rpaths), paddle_inference_so_file)
if platform.machine() != 'sw_64' and platform.machine() != 'mips64':
assert os.system(
command) == 0, "patchelf {} failed, the command: {}".format(