Skip to content

High performance self-hosted photo and video management solution.

chore(ml): downgrade to cuda 12.2 (#12587)

Mertad58d7e23edd
diff --git a/docs/docs/features/ml-hardware-acceleration.md b/docs/docs/features/ml-hardware-acceleration.md
index b20c3fc2b6..9f2d33cc35 100644
--- a/docs/docs/features/ml-hardware-acceleration.md
+++ b/docs/docs/features/ml-hardware-acceleration.md
@@ -38,7 +38,7 @@ You do not need to redo any machine learning jobs after enabling hardware accele
- The GPU must have compute capability 5.2 or greater.
- The server must have the official NVIDIA driver installed.
-- The installed driver must be >= 545 (it must support CUDA 12.3.2).
+- The installed driver must be >= 535 (it must support CUDA 12.2).
- On Linux (except for WSL2), you also need to have [NVIDIA Container Toolkit][nvct] installed.
#### OpenVINO
diff --git a/machine-learning/Dockerfile b/machine-learning/Dockerfile
index baeefbf0d8..e49fde1464 100644
--- a/machine-learning/Dockerfile
+++ b/machine-learning/Dockerfile
@@ -49,7 +49,12 @@ RUN apt-get update && \
apt-get remove wget -yqq && \
rm -rf /var/lib/apt/lists/*
-FROM nvidia/cuda:12.3.2-cudnn9-runtime-ubuntu22.04@sha256:fa44193567d1908f7ca1f3abf8623ce9c63bc8cba7bcfdb32702eb04d326f7a8 AS prod-cuda
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04@sha256:94c1577b2cd9dd6c0312dc04dff9cb2fdce2b268018abc3d7c2dbcacf1155000 AS prod-cuda
+
+RUN apt-get update && \
+ apt-get install --no-install-recommends -yqq libcudnn9-cuda-12 && \
+ apt-get clean && \
+ rm -rf /var/lib/apt/lists/*
COPY --from=builder-cuda /usr/local/bin/python3 /usr/local/bin/python3
COPY --from=builder-cuda /usr/local/lib/python3.11 /usr/local/lib/python3.11