Hugging Face's logo

raazkumar
/
ml-intern-local-fork

Model card Files
xet
 Community
ml-intern-local-fork
File size: 2,810 Bytes
838f982
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
replicaCount:
  api: 2
  worker: 2

image:
  repository: ml-intern
  pullPolicy: IfNotPresent
  tag: "latest"

imagePullSecrets: []
nameOverride: ""
fullnameOverride: ""

serviceAccount:
  create: true
  annotations: {}
  name: ""

podAnnotations:
  prometheus.io/scrape: "true"
  prometheus.io/port: "8000"
  prometheus.io/path: "/metrics"

podSecurityContext:
  fsGroup: 1000

securityContext:
  runAsNonRoot: true
  runAsUser: 1000
  capabilities:
    drop:
      - ALL
  readOnlyRootFilesystem: true
  allowPrivilegeEscalation: false

service:
  type: ClusterIP
  port: 8000

ingress:
  enabled: false
  className: "nginx"
  annotations:
    nginx.ingress.kubernetes.io/rate-limit: "100"
    nginx.ingress.kubernetes.io/rate-limit-window: "1m"
  hosts:
    - host: ml-intern.local
      paths:
        - path: /
          pathType: Prefix
  tls: []

resources:
  api:
    requests:
      cpu: 250m
      memory: 512Mi
    limits:
      cpu: 2000m
      memory: 2Gi
  worker:
    requests:
      cpu: 100m
      memory: 256Mi
    limits:
      cpu: 1000m
      memory: 1Gi

autoscaling:
  enabled: true
  api:
    minReplicas: 2
    maxReplicas: 20
    targetCPUUtilizationPercentage: 70
    targetMemoryUtilizationPercentage: 80
    scaleUpStabilizationWindowSeconds: 60
    scaleDownStabilizationWindowSeconds: 300

nodeSelector: {}

tolerations: []

affinity:
  api:
    podAntiAffinity:
      preferredDuringSchedulingIgnoredDuringExecution:
        - weight: 100
          podAffinityTerm:
            labelSelector:
              matchExpressions:
                - key: app.kubernetes.io/name
                  operator: In
                  values:
                    - ml-intern
            topologyKey: kubernetes.io/hostname

config:
  port: 8000
  workers: 4
  maxConcurrentRequests: 200
  defaultRpmLimit: 40
  requestTimeout: 120
  cacheTtlSeconds: 300
  budgetUsdPerSession: 10.0
  circuitBreaker:
    failureThreshold: 5
    recoveryTimeout: 60
  logLevel: INFO

secrets:
  hfToken: ""
  anthropicApiKey: ""
  openaiApiKey: ""
  groqApiKey: ""
  nvidiaApiKey: ""

redis:
  enabled: true
  architecture: standalone
  auth:
    enabled: false
  master:
    persistence:
      enabled: true
      size: 5Gi
    resources:
      requests:
        memory: 256Mi
        cpu: 100m
      limits:
        memory: 1Gi
        cpu: 500m

postgresql:
  enabled: true
  auth:
    username: ml_intern
    password: ml_intern
    database: ml_intern
  primary:
    persistence:
      enabled: true
      size: 10Gi
    resources:
      requests:
        memory: 256Mi
        cpu: 100m
      limits:
        memory: 1Gi
        cpu: 500m

monitoring:
  enabled: true
  prometheus:
    enabled: true
    retention: "30d"
  grafana:
    enabled: true
    adminPassword: "admin"
  jaeger:
    enabled: true