78 lines
2.0 KiB
YAML
78 lines
2.0 KiB
YAML
# -*- coding: utf-8 -*-
|
||
# iAOP Helm Chart 默认 values(PRD 5.6「⑥ 部署底座」配置点)。
|
||
#
|
||
# 切换推理后端(NVIDIA 5090 GPU ↔ 华为昇腾 NPU)只需改:
|
||
# inference.backend: gpu | npu
|
||
# 其余部署(内核+模板、资源配额、灰度、存储、域名)无需改动。
|
||
|
||
# ---- 镜像 ----
|
||
image:
|
||
repository: iaop/inference
|
||
tag: v1.0.0
|
||
pullPolicy: IfNotPresent
|
||
# 私有仓库拉取凭据(imagePullSecrets)
|
||
pullSecrets: []
|
||
# 服务账户(缺省 = release 名;自定义请先创建)
|
||
serviceAccountName: ""
|
||
|
||
# ---- 推理后端选择(PRD 5.6 配置点:切换后端仅改此处) ----
|
||
inference:
|
||
backend: gpu # gpu | npu
|
||
model: iaop-ti-cl4-v1
|
||
runtime: vllm # gpu: vllm|triton;npu: mindie|onnx-ascend
|
||
device: nvidia-5090 # gpu: nvidia-5090;npu: ascend-310p|ascend-910b
|
||
cannVersion: "" # npu: CANN 工具链版本(如 "8.0"),gpu 忽略
|
||
maxTokens: 1024
|
||
temperature: 0.1
|
||
timeoutSeconds: 60
|
||
|
||
# ---- 副本与滚动(灰度发布策略,PRD 5.6 配置点) ----
|
||
replicaCount: 2
|
||
rollingUpdate:
|
||
maxUnavailable: 0
|
||
maxSurge: 1
|
||
|
||
# ---- 水平自动扩缩(HPA;副本参数化扩展,issue #56) ----
|
||
autoscaling:
|
||
enabled: false
|
||
minReplicas: 2
|
||
maxReplicas: 8
|
||
targetCPUUtilizationPercentage: 70
|
||
|
||
# ---- 节点调度(可选) ----
|
||
tolerations: [] # 容忍度(如 GPU/NPU 专用节点污点)
|
||
|
||
# ---- 服务 ----
|
||
service:
|
||
type: ClusterIP
|
||
port: 8000
|
||
|
||
# ---- 域名入口 ----
|
||
ingress:
|
||
enabled: false
|
||
host: iaop.example.com
|
||
className: ""
|
||
|
||
# ---- 资源配额(PRD 5.6 配置点) ----
|
||
resources:
|
||
requests:
|
||
cpu: "2"
|
||
memory: 8Gi
|
||
limits:
|
||
cpu: "8"
|
||
memory: 32Gi
|
||
|
||
# ---- 存储(模型权重/日志持久化) ----
|
||
storage:
|
||
enabled: true
|
||
className: "" # 空 = 使用集群默认 StorageClass
|
||
size: 100Gi
|
||
|
||
# ---- 探针 ----
|
||
livenessProbe:
|
||
initialDelaySeconds: 30
|
||
periodSeconds: 10
|
||
readinessProbe:
|
||
initialDelaySeconds: 10
|
||
periodSeconds: 5
|