orign 0.2.3

A globally distributed container orchestrator
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38

apiVersion: v1
kind: Pod
metadata:
  name: llama-factory
  namespace: orign
spec:
  containers:
  - image: swr.cn-east-317.qdrgznjszx.com/donggang/llama-factory-ascend910:cann8-py310-torch2.2.0-ubuntu18.04
    imagePullPolicy: Always
    name: llama-factory
    ports:
    - containerPort: 8000
      protocol: TCP
    resources:
      limits:
        memory: 40Gi
        nvidia.com/gpu: "1"
      requests:
        memory: 40Gi
        nvidia.com/gpu: "1"
    volumeMounts:
    - mountPath: /root/.cache/huggingface
      name: huggingface-cache
  nodeSelector:
    gpu-type: l40s-2xlarge
    role: gpu
  tolerations:
  - effect: NoSchedule
    key: gpu
    operator: Equal
    value: "true"
  - effect: NoSchedule
    key: nvidia.com/gpu
    operator: Exists
  volumes:
  - name: huggingface-cache
    persistentVolumeClaim:
      claimName: huggingface-cache-pvc