A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 08:15 UTC
Make shutil rename in python_only_dev (#10233)
Signed-off-by: shcheglovnd <shcheglovnd@avride.ai>
Nikolai Shcheglov committed
Nov 11, 2024 at 16:29 UTC
08f93e743972abd3060723f63352ef42cdf161a8
1 file changed
+2
-1
python_only_dev.py
+2
-1
@@ -69,7 +69,8 @@ if not args.quit_dev:
69
current_vllm_path = os.path.join(cwd, "vllm")
70
71
print(f"Renaming {pre_built_vllm_path} to {tmp_path} for backup")
72
- os.rename(pre_built_vllm_path, tmp_path)
72
+ shutil.copytree(pre_built_vllm_path, tmp_path)
73
+ shutil.rmtree(pre_built_vllm_path)
74
75
print(f"Linking {current_vllm_path} to {pre_built_vllm_path}")
76
os.symlink(current_vllm_path, pre_built_vllm_path)