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
[Bugfix][CI][CPU] add missing datasets package to requirements-cpu.txt (#11159)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Dec 13, 2024 at 16:50 UTC
f93bf2b1897cca5b644fe03f31925e4faff40056
1 file changed
+2
-1
requirements-cpu.txt
+2
-1
@@ -4,4 +4,5 @@
4
# Dependencies for CPUs
5
torch==2.5.1+cpu; platform_machine != "ppc64le" and platform_machine != "aarch64"
6
torch==2.5.1; platform_machine == "aarch64"
7
-torchvision; platform_machine != "ppc64le" # required for the image processor of phi3v, this must be updated alongside torch
\ No newline at end of file
7
+torchvision; platform_machine != "ppc64le" # required for the image processor of phi3v, this must be updated alongside torch
8
+datasets # for benchmark scripts
\ No newline at end of file