Served models on tainted GPU nodes can't get Longhorn storage

Found while testing #117 live on an AWS Nebari cluster.

When GPU nodes carry a taint (e.g. nvidia.com/gpu) and Longhorn's components do not tolerate it, longhorn-manager is not scheduled on the GPU nodes, so they never register as Longhorn nodes and Longhorn cannot attach PVCs there:

FailedAttachVolume: ... unable to attach volume <pvc> to <gpu-node>:
node.longhorn.io "<gpu-node>" not found

The pack defaults model storage to the longhorn StorageClass (defaults.storage.storageClassName), so a served LLMModel scheduled onto a tainted GPU node gets stuck in Init with its model-storage PVC unattached, and never serves.

Workaround (per model): set spec.model.storage.storageClassName to a class that attaches on the GPU node, e.g. gp2/EBS (WaitForFirstConsumer, provisions in the node's AZ).

Suggested fix: document this for GPU node groups, and/or default served-model storage to a node-local class when the model requests a GPU. Not addressed by code yet.

Review the model storage defaults at defaults.storage.storageClassName and the per-model spec.model.storage.storageClassName setting, along with the GPU-node scheduling behavior described in the issue. Done means documenting the Longhorn and tainted-node limitation for GPU node groups, or resolving and implementing an agreed default-storage behavior for GPU models.