Add fabric manager boot and support diagnostics
This commit is contained in:
@@ -43,6 +43,7 @@ systemctl enable bee-journal-mirror@ttyS1.service 2>/dev/null || true
|
||||
# Enable GPU-vendor specific services
|
||||
if [ "$GPU_VENDOR" = "nvidia" ]; then
|
||||
systemctl enable nvidia-dcgm.service 2>/dev/null || true
|
||||
systemctl enable nvidia-fabricmanager.service 2>/dev/null || true
|
||||
systemctl enable bee-nvidia.service
|
||||
elif [ "$GPU_VENDOR" = "amd" ]; then
|
||||
# ROCm symlinks (packages install to /opt/rocm-*/bin/)
|
||||
|
||||
@@ -5,6 +5,7 @@
|
||||
# DCGM 4 is packaged per CUDA major. The image ships NVIDIA driver 590 with
|
||||
# CUDA 13 userspace, so install the CUDA 13 build plus proprietary components
|
||||
# explicitly.
|
||||
nvidia-fabricmanager=%%NVIDIA_FABRICMANAGER_VERSION%%
|
||||
datacenter-gpu-manager-4-cuda13=1:%%DCGM_VERSION%%
|
||||
datacenter-gpu-manager-4-proprietary=1:%%DCGM_VERSION%%
|
||||
datacenter-gpu-manager-4-proprietary-cuda13=1:%%DCGM_VERSION%%
|
||||
|
||||
Reference in New Issue
Block a user