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, 09:30 UTC
[Misc] Specify minimum pynvml version (#9827)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Oct 30, 2024 at 14:05 UTC
6aa6020f9bd4c1e414c10f7bd3a7c2555f1950b2
1 file changed
+1
-1
requirements-cuda.txt
+1
-1
@@ -3,7 +3,7 @@
3
4
# Dependencies for NVIDIA GPUs
5
ray >= 2.9
6
-nvidia-ml-py # for pynvml package
6
+nvidia-ml-py >= 12.560.30 # for pynvml package
7
torch == 2.5.0
8
# These must be updated alongside torch
9
torchvision == 0.20 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version