feat: 完成 issue #8 ⑥ K8s/Helm 部署底座 + 昇腾适配层
This commit is contained in:
@@ -0,0 +1,63 @@
|
||||
# -*- 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
|
||||
|
||||
# ---- 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
|
||||
|
||||
# ---- 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
|
||||
Reference in New Issue
Block a user