19 lines
860 B
YAML
19 lines
860 B
YAML
|
# Cluster-scoped prerequisite for every GPU workload on worker-1.
|
||
|
|
#
|
||
|
|
# The Talos nvidia-container-toolkit extension already registers the containerd
|
||
|
|
# runtime handler (/etc/cri/conf.d/10-nvidia-container-runtime.part ->
|
||
|
|
# plugins."io.containerd.cri.v1.runtime".containerd.runtimes.nvidia), but the
|
||
|
|
# Kubernetes RuntimeClass object is separate and is NOT created by the
|
||
|
|
# extension. Without it every pod carrying runtimeClassName: nvidia is rejected
|
||
|
|
# at admission with:
|
||
|
|
# pods "..." is forbidden: pod rejected: RuntimeClass "nvidia" not found
|
||
|
|
#
|
||
|
|
# Deliberately NOT setting nvidia as containerd's default_runtime_name (the
|
||
|
|
# 20-customization.part patch in the Talos guide): that would route every pod on
|
||
|
|
# the node through the NVIDIA runtime. Opting in per-pod is narrower.
|
||
|
|
apiVersion: node.k8s.io/v1
|
||
|
|
kind: RuntimeClass
|
||
|
|
metadata:
|
||
|
|
name: nvidia
|
||
|
|
handler: nvidia
|