@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 7c7aa37c69
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, 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: