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 15, 09:45 UTC
Update cpu.txt (#18398)
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
汪志鹏 committed
May 20, 2025 at 18:53 UTC
d6c86d09aecb910fd336ba83ede70265ee81149a
1 file changed
+2
requirements/cpu.txt
+2
@@ -2,6 +2,8 @@
2
-r common.txt
3
4
# Dependencies for CPUs
5
+packaging>=24.2
6
+setuptools>=77.0.3,<80.0.0
7
--extra-index-url https://download.pytorch.org/whl/cpu
8
torch==2.7.0+cpu; platform_machine == "x86_64"
9
torch==2.7.0; platform_system == "Darwin"