通过kubectl命令行创建NPU应用 本节以创建无状态工作负载(Deployment)为例,说明使用kubectl命令创建训练任务的方法。 apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
description: ''
labels:
appgroup: ''
version: v1
name: demo
namespace: default
spec:
selector:
matchLabels:
app: demo
version: v1
template:
metadata:
labels:
app: demo
version: v1
spec:
containers:
- name: container-1
image: swr.cn-north-7.myhuaweicloud.com/ief-ies/demo:latest
imagePullPolicy: IfNotPresent
env:
- name: PAAS_APP_NAME
value: demo
- name: PAAS_NAMESPACE
value: default
- name: PAAS_PROJECT_ID
value: 0aa612a71f80d4322fe0c010beb80e8a
resources:
requests:
cpu: 250m
memory: 512Mi
huawei.com/ascend-1980: '1' ##需要使用的npu卡数量
limits:
cpu: 250m
memory: 512Mi
huawei.com/ascend-1980: '1' ##需要使用的npu卡数量
terminationGracePeriodSeconds: 30
schedulerName: volcano ## 使用的调度器指定为volcano
tolerations:
- key: node.kubernetes.io/not-ready
operator: Exists
effect: NoExecute
tolerationSeconds: 300
- key: node.kubernetes.io/unreachable
operator: Exists
effect: NoExecute
tolerationSeconds: 300
initContainers: []
volumes: []
replicas: 2
revisionHistoryLimit: 10
strategy:
type: RollingUpdate
rollingUpdate:
maxUnavailable: 25%
maxSurge: 25%
progressDeadlineSeconds: 600