@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 08f93e7439
Fork 0

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)