Files
ocdp_chart/llama-factory/llama-factory/templates/single.yaml
2025-09-23 10:01:17 +08:00

52 lines
1.4 KiB
YAML

{{- if eq (int .Values.workerSize) 1 }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ .Release.Name }}
spec:
replicas: {{ .Values.replicaCount }}
selector:
matchLabels:
app: llama-factory
template:
metadata:
labels:
app: llama-factory
spec:
containers:
- name: llama-factory
image: {{ .Values.llama.image }}
imagePullPolicy: IfNotPresent
env:
- name: HUGGING_FACE_HUB_TOKEN
value: {{ .Values.vllm.huggingfaceToken }}
command:
- sh
- -c
- "llamafactory-cli webui"
resources:
limits:
nvidia.com/gpu: "{{ .Values.resources.gpuLimit }}"
memory: {{ .Values.resources.memoryLimit }}
ephemeral-storage: 10Gi
requests:
ephemeral-storage: 10Gi
cpu: {{ .Values.resources.cpuRequest }}
ports:
- containerPort: 7860
name: http
volumeMounts:
- mountPath: /dev/shm
name: dshm
- name: weight-volume
mountPath: {{ .Values.model.localMountPath }}
volumes:
- name: dshm
emptyDir:
medium: Memory
sizeLimit: {{ .Values.resources.shmSize }}
- name: weight-volume
persistentVolumeClaim:
claimName: {{ .Values.app}}-pvc-model
{{- end }}