@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 4004f144f3
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, 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(".")