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, 02:00 UTC
[Build] update requirements of no-device (#12299)
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Mengqing Cao committed
Jan 22, 2025 at 14:29 UTC
4004f144f370f9d42c92e2edce5e5db1b453d57a
1 file changed
+1
-1
setup.py
+1
-1
@@ -549,7 +549,7 @@ def get_requirements() -> List[str]:
549
return resolved_requirements
550
551
if _no_device():
552
- requirements = _read_requirements("requirements-cuda.txt")
552
+ requirements = _read_requirements("requirements-cpu.txt")
553
elif _is_cuda():
554
requirements = _read_requirements("requirements-cuda.txt")
555
cuda_major, cuda_minor = torch.version.cuda.split(".")