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 13, 07:00 UTC
[Bugfix] [CPU] bump torch to 2.9.0 for Darwin to fix segmentation fault (#27791)
Signed-off-by: Kebe <mail@kebe7jun.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
Kebe committed
Nov 14, 2025 at 05:48 UTC
faed7bf07ec831529c5ed54e15b21e30b30dc16e
1 file changed
+1
-1
requirements/cpu.txt
+1
-1
@@ -8,7 +8,7 @@ packaging>=24.2
8
setuptools>=77.0.3,<81.0.0
9
--extra-index-url https://download.pytorch.org/whl/cpu
10
torch==2.8.0+cpu; platform_machine == "x86_64" or platform_machine == "s390x"
11
-torch==2.8.0; platform_system == "Darwin"
11
+torch==2.9.0; platform_system == "Darwin"
12
torch==2.8.0; platform_machine == "ppc64le" or platform_machine == "aarch64"
13
14
# required for the image processor of minicpm-o-2_6, this must be updated alongside torch