43 lines
744 B
YAML
43 lines
744 B
YAML
nameOverride: "nccl-test"
|
|
replicaCount: 2
|
|
|
|
image:
|
|
repository: nvcr.io/nvidia/pytorch
|
|
tag: "24.10-py3"
|
|
pullPolicy: IfNotPresent
|
|
|
|
training:
|
|
nprocPerNode: 8
|
|
masterPort: 29500
|
|
batchSize: 1200
|
|
epochs: 90
|
|
lr: 0.01
|
|
|
|
resources:
|
|
gpu: 8
|
|
hostdev: 2
|
|
|
|
shmSize: "128Gi"
|
|
|
|
network:
|
|
nadName: "hostdevice-net"
|
|
resourceName: "hostdev"
|
|
networkNamespace: "nvidia-network-operator"
|
|
ipam:
|
|
range: "10.200.0.0/28"
|
|
exclude:
|
|
- "10.200.0.0"
|
|
- "10.200.0.15"
|
|
|
|
nccl:
|
|
debug: "INFO"
|
|
debugSubsys: "INIT,NET,IB"
|
|
ibDisable: 0
|
|
socketIfname: "net"
|
|
ibHCA: "" # 비어있으면 설정 안 함
|
|
debugFile: "" # 비어있으면 설정 안 함
|
|
|
|
volumes:
|
|
dataset:
|
|
hostPath: "/home/ubuntu/cifar-10-batches-py"
|