feat: add llm-monitor

helm-charts/llm-monitor/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

helm-charts/llm-monitor/Chart.lock

@@ -0,0 +1,12 @@
+dependencies:
+- name: prometheus
+  repository: https://prometheus-community.github.io/helm-charts
+  version: 27.23.0
+- name: grafana
+  repository: https://grafana.github.io/helm-charts
+  version: 9.2.10
+- name: dcgm-exporter
+  repository: https://nvidia.github.io/dcgm-exporter/helm-charts
+  version: 4.1.3
+digest: sha256:1c729d94953ff3bd72267f0337e2729e19d3b81d727bf63f8b1b3775fc103229
+generated: "2025-07-07T17:28:37.577073+08:00"

helm-charts/llm-monitor/Chart.yaml

@@ -0,0 +1,39 @@
+apiVersion: v2
+name: llm-monitor
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.16.0"
+
+dependencies:
+- name: prometheus
+  condition: prometheus.enabled
+  version: "~27.23.0"
+  repository: "https://prometheus-community.github.io/helm-charts"
+- name: grafana
+  condition: grafana.enabled
+  version: "~9.2.10"
+  repository: "https://grafana.github.io/helm-charts"
+- name: dcgm-exporter
+  condition: dcgm-exporter.enabled
+  version: "~4.1.3"
+  repository: "https://nvidia.github.io/dcgm-exporter/helm-charts"
+

helm-charts/llm-monitor/README_zh.md

@@ -0,0 +1,28 @@
+# llm-monitor
+
+## 安装
+
+```bash
+kubectl create ns monitor
+helm -n monitor install llm-monitor -f values.yaml .
+```
+
+## 使用
+
+### 访问 prometheus
+
+```bash
+PROM_IP=$(kubectl -n monitor get svc | grep prometheus-server | awk '{print $4}')
+echo "访问 'http://${PROM_IP}' 查看 prometheus"
+```
+
+### 访问 grafana
+
+```bash
+GRAFANA_HOST=$(kubectl -n monitor get svc | grep grafana | awk '{print $4}')
+GRAFANA_PASSWD=$(kubectl -n monitor get secret llm-monitor-grafana -o jsonpath="{.data.admin-password}" | base64 --decode)
+echo "访问 'http://${GRAFANA_HOST}' 查看 grafana"
+echo "账号: 'admin'"
+echo "密码: '${GRAFANA_PASSWD}'"
+```
+