29 Star 36 Fork 74

Ascend/mindxdl-deploy
暂停

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
infer-deploy-dynamic.yaml 1.78 KB
一键复制 编辑 原始数据 按行查看 历史
apiVersion: apps/v1
kind: Deployment
metadata:
name: resnetinfer1-1-deploy
labels:
app: infers
spec:
replicas: 1
selector:
matchLabels:
app: infers
template:
metadata:
labels:
app: infers
fault-scheduling: grace # Add this Labels, will reschedule pods in the event of chip failures.
ring-controller.atlas: ascend-310P # Add this Label, used to check job kind.
vnpu-dvpp: "null" # For NPU dynamic segmentation,null means don't care dvpp resource ,yes means used dvpp,no means ndvpp
vnpu-level: low # For NPU dynamic segmentation,low means low-level configuration,high means performance first,default low.
spec:
schedulerName: volcano
automountServiceAccountToken: false
nodeSelector:
host-arch: huawei-arm # Select the os arch. If the os arch is x86, change it to huawei-x86.
containers:
- image: ubuntu-infer:v1 # Inference image name
imagePullPolicy: IfNotPresent
name: resnet50infer
resources:
requests:
huawei.com/npu-core: 1 # Number of required NPUs. The maximum value is 8. You can add lines below to configure resources such as memory and CPU.
limits:
huawei.com/npu-core: 1 # The value should be the same as that of requests .
volumeMounts:
- name: slog
mountPath: /var/log/npu/conf/slog/ #Log path
- name: localtime #The container time must be the same as the host time.
mountPath: /etc/localtime
volumes:
- name: slog
hostPath:
path: /var/log/npu/conf/slog/
- name: localtime
hostPath:
path: /etc/localtime
Loading...
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
其他
1
https://gitee.com/ascend/mindxdl-deploy.git
git@gitee.com:ascend/mindxdl-deploy.git
ascend
mindxdl-deploy
mindxdl-deploy
master

搜索帮助