# NVIDIA DCGM (Data Center GPU Manager).
# Validate uses dcgmi diagnostics; Burn uses dcgmproftester as the official
# NVIDIA max-compute recipe. The smoketest/runtime contract treats
# dcgmproftester as required in the LiveCD.
# DCGM 4 is packaged per CUDA major. The image ships NVIDIA driver 580 with
# CUDA 13 userspace, so install the CUDA 13 build plus proprietary components
# explicitly. datacenter-gpu-manager-4-core must be pinned too, not just the
# cuda13/proprietary variants that depend on it: without an explicit version,
# apt's solver picks the newest core in the repo and then reports the
# versioned deps as unmet instead of resolving to the pinned version.
nvtop
nvidia-fabricmanager=%%NVIDIA_FABRICMANAGER_VERSION%%
datacenter-gpu-manager-4-core=1:%%DCGM_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%%
ocl-icd-libopencl1
clinfo

# 4th-gen NVSwitch (NVLink5) support for HGX/DGX B100/B200/B300. Neither
# nvidia-fabricmanager nor datacenter-gpu-manager declare these as apt
# dependencies (confirmed against the cuda-repo Packages index), so the
# fabricmanager start script and DCGM's NVSwitch backend silently fail
# without them:
#   - libibumad3: userspace lib nvidia-fabricmanager-start.sh needs to poll
#     the CX7 management NIC (mlx5_*) before training the NVSwitch fabric.
#     Comes from Debian's rdma-core, not the cuda-repo.
#   - nvlsm: InfiniBand-compliant Subnet Manager. FM's own start script
#     launches it internally on NVL5+ systems once present — no separate
#     systemd unit to enable. Versioned independently of the driver branch.
#   - libnvidia-nscq: NVSwitch query library DCGM dlopens at runtime for
#     `dcgmi diag`/health monitoring on NVSwitch systems; must match the
#     driver branch like nvidia-fabricmanager does.
libibumad3
nvlsm
libnvidia-nscq=%%NVIDIA_FABRICMANAGER_VERSION%%