Unable to run with intel GPU

[urbaman]

Hi,

See here, I cannot seem to run with intel gpu.

Here's my values:

replicaCount: 1

deployment:
  image:
    repository: quay.io/go-skynet/local-ai
    tag: latest-aio-gpu-intel-f32    # Use the appropriate tag. E.g. for cpu only: "latest-cpu"
  env:
    threads: 4
    context_size: 512
    DEBUG: true

  # # Inject Secrets into Environment:
  # secretEnv:
  # - name: HF_TOKEN
  #   valueFrom:
  #     secretKeyRef:
  #       name: some-secret
  #       key: hf-token

  modelsPath: "/models"
  prompt_templates:
    # To use cloud provided (eg AWS) image, provide it like: 1234356789.dkr.ecr.us-REGION-X.amazonaws.com/busybox
    image: busybox
  pullPolicy: IfNotPresent
  imagePullSecrets: []
    # - name: secret-names

  ## Needed for GPU Nodes
  #runtimeClassName: gpu

resources:
  limits:
    gpu.intel.com/i915: "1"
  # {}
  # We usually recommend not to specify default resources and to leave this as a conscious
  # choice for the user. This also increases chances charts run on environments with little
  # resources, such as Minikube. If you do want to specify resources, uncomment the following
  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
  # limits:
  #   cpu: 100m
  #   memory: 128Mi
  # requests:
  #   cpu: 100m
  #   memory: 128Mi

# Model config to include
modelsConfigs:
  {}
  # phi-2: |
  #   name: phi-2
  #   context_size: 2048
  #   f16: true
  #   mmap: true
  #   trimsuffix:
  #   - "\n"
  #   parameters:
  #     model: phi-2.Q8_0.gguf
  #     temperature: 0.2
  #     top_k: 40
  #     top_p: 0.95
  #     seed: -1
  #   template:
  #     chat: &template |-
  #       Instruct: {{.Input}}
  #       Output:
  #     completion: *template

# Prompt templates to include
# Note: the keys of this map will be the names of the prompt template files
promptTemplates:
  {}
  # ggml-gpt4all-j.tmpl: |
  #   The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
  #   ### Prompt:
  #   {{.Input}}
  #   ### Response:

initContainers: []
# Example:
# - name: my-init-container
#   image: my-init-image
#   imagePullPolicy: IfNotPresent
#   command: ["/bin/sh", "-c", "echo init"]
#   volumeMounts:
#     - name: my-volume
#       mountPath: /path/to/mount

sidecarContainers: []
# Example:
# - name: my-sidecar-container
#   image: my-sidecar-image
#   imagePullPolicy: IfNotPresent
#   ports:
#     - containerPort: 1234

# Persistent storage for models and prompt templates.
# PVC and HostPath are mutually exclusive. If both are enabled,
# PVC configuration takes precedence. If neither are enabled, ephemeral
# storage is used.
persistence:
  models:
    enabled: true
    annotations: {}
    storageClass: "" # Use default storage class
    accessModes:
      - ReadWriteMany
    size: 10Gi
    globalMount: /build/models
  output:
    enabled: true
    annotations: {}
    storageClass: "" # Use default storage class
    accessModes:
      - ReadWriteMany
    size: 5Gi
    globalMount: /tmp/generated

service:
  type: ClusterIP
  # If deferring to an internal only load balancer
  # externalTrafficPolicy: Local
  port: 80
  nodePort:
  annotations: {}
  # If using an AWS load balancer, you'll need to override the default 60s load balancer idle timeout
  # service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: "1200"

ingress:
  enabled: false
  className: ""
  annotations:
    {}
    # nginx.ingress.kubernetes.io/proxy-body-size: "25m" # This value determines the maxmimum uploadable file size
    # kubernetes.io/ingress.class: nginx
    # kubernetes.io/tls-acme: "true"
  hosts:
    - host: chart-example.local
      paths:
        - path: /
          pathType: ImplementationSpecific
  tls: []
  #  - secretName: chart-example-tls
  #    hosts:
  #      - chart-example.local

nodeSelector: {}

tolerations: []

affinity: {}