> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Nodes

> [card] [How do I interpret GPU health events?](https://docs.coreweave.com/support/cks/articles/how-do-i-interpret-gpu-health-events)
>
> CoreWeave surfaces NVIDIA GPU health signals, including XID counts (driver-reported errors) and thermal data, through th ...

> [card] [How do I request specific GPU types using Node selectors?](https://docs.coreweave.com/support/cks/articles/how-do-i-request-specific-gpu-types-using-node-selectors)
>
> Use a nodeSelector (or nodeAffinity) on your Pod to target a specific GPU type. CoreWeave labels GPU Nodes with hardware ...

> [card] [What are interruptible labels and how do they affect Node maintenance?](https://docs.coreweave.com/support/cks/articles/what-are-interruptible-labels-and-how-do-they-affect-node-maintenance)
>
> Interruptible labels are Pod-level labels that control how CKS handles a Pod during Node maintenance, reboots, or scale- ...

> [card] [What do GPU XID error codes mean and what should I do?](https://docs.coreweave.com/support/cks/articles/what-do-gpu-xid-error-codes-mean)
>
> An XID is an error report from the NVIDIA driver, written to the kernel log of the Node that hosts the GPU. Not every XI ...

> [card] [Why did my Nodes go NotReady after I deployed Tailscale?](https://docs.coreweave.com/support/cks/articles/why-did-my-nodes-go-notready-after-i-deployed-tailscale)
>
> A self-managed Tailscale workload that uses hostNetwork: true can change the Node's firewall rules. These changes can di ...

> [card] [Why does the autoscaler remove Nodes that are still running my workload?](https://docs.coreweave.com/support/cks/articles/why-does-the-autoscaler-remove-nodes-running-active-workloads)
>
> The Kubernetes Cluster Autoscaler decides that a Node is unneeded using its own utilization-based logic. It does not con ...

> [card] [Why won't my Node Pool scale down after my Jobs finish?](https://docs.coreweave.com/support/cks/articles/why-wont-my-node-pool-scale-down-after-my-jobs-finish)
>
> Finished Job Pods are normally in the Succeeded or Failed phase and don't block scale-down. The CKS idle check (CWActive ...
