ComfyUI pod in pending state

[krishnajugal]

The two nodes created in the cluster is running on t3x.large instance type. Is this expected or it should be running on a gpu instance type like g4dn??

$ kubectl describe pod comfyui-6cd777d4f-2hpkl
Name: comfyui-6cd777d4f-2hpkl
Namespace: default
Priority: 0
Service Account: default
Node:
Labels: app=comfyui
pod-template-hash=6cd777d4f
Annotations:
Status: Pending
IP:
IPs:
Controlled By: ReplicaSet/comfyui-6cd777d4f
Containers:
comfyui:
Image: 397016254480.dkr.ecr.us-west-2.amazonaws.com/comfyui-images:latest
Port: 8848/TCP
Host Port: 0/TCP
Limits:
nvidia.com/gpu: 1
Requests:
nvidia.com/gpu: 1
Environment:
Mounts:
/app/ComfyUI/models from stable-diffusion-models (rw)
/app/ComfyUI/output from comfyui-outputs (rw)
/var/run/secrets/kubernetes.io/serviceaccount from kube-api-access-t5mtf (ro)
Conditions:
Type Status
PodScheduled False
Volumes:
stable-diffusion-models:
Type: HostPath (bare host directory volume)
Path: /comfyui-models
HostPathType:
comfyui-outputs:
Type: PersistentVolumeClaim (a reference to a PersistentVolumeClaim in the same namespace)
ClaimName: comfyui-outputs-pvc
ReadOnly: false
kube-api-access-t5mtf:
Type: Projected (a volume that contains injected data from multiple sources)
TokenExpirationSeconds: 3607
ConfigMapName: kube-root-ca.crt
ConfigMapOptional:
DownwardAPI: true
QoS Class: BestEffort
Node-Selectors:
Tolerations: node.kubernetes.io/not-ready:NoExecute op=Exists for 300s
node.kubernetes.io/unreachable:NoExecute op=Exists for 300s
nvidia.com/gpu:NoSchedule op=Exists
Events:
Type Reason Age From Message

---

Normal Nominated 51m karpenter Pod should schedule on: nodeclaim/karpenter-nodepool-ztcrj
Normal Nominated 35m karpenter Pod should schedule on: nodeclaim/karpenter-nodepool-7bqxl
Normal Nominated 19m karpenter Pod should schedule on: nodeclaim/karpenter-nodepool-dzsgk
Normal Nominated 3m54s karpenter Pod should schedule on: nodeclaim/karpenter-nodepool-2vbdk
Warning FailedScheduling 77s (x244 over 20h) default-scheduler 0/2 nodes are available: 2 Insufficient nvidia.com/gpu. preemption: 0/2 nodes are available: 2 No preemption victims found for incoming pod.