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, 04:30 UTC
[CI/Build] fix pre-compiled wheel install for exact tag (#11373)
Signed-off-by: Daniele Trifirò <dtrifiro@redhat.com>
Daniele committed
Dec 20, 2024 at 17:14 UTC
7c7aa37c6933c40a94da0789d0f330a8d89f091b
1 file changed
+1
-1
setup.py
+1
-1
@@ -466,7 +466,7 @@ def get_vllm_version() -> str:
466
version += f"{sep}empty"
467
elif _is_cuda():
468
if envs.VLLM_USE_PRECOMPILED:
469
- version += ".precompiled"
469
+ version += f"{sep}precompiled"
470
else:
471
cuda_version = str(get_nvcc_cuda_version())
472
if cuda_version != MAIN_CUDA_VERSION: