66 lines
1.5 KiB
YAML
66 lines
1.5 KiB
YAML
|
image:
|
||
|
|
repository: tytn/fabulinus
|
||
|
|
pullPolicy: IfNotPresent
|
||
|
|
tag: latest-cpu@sha256:f8b30eaa5b61d6085fc715f40619733846927c2266a3e20523e93fb58afeef38
|
||
|
|
gpuImage:
|
||
|
|
repository: tytn/fabulinus
|
||
|
|
pullPolicy: IfNotPresent
|
||
|
|
tag: latest-gpu@sha256:9a826a578ca4157fbe3c091eb78aa35dfca6675f9fae24dcb90495ba4d9715d1
|
||
|
|
|
||
|
|
securityContext:
|
||
|
|
container:
|
||
|
|
readOnlyRootFilesystem: false
|
||
|
|
runAsUser: 0
|
||
|
|
runAsGroup: 0
|
||
|
|
|
||
|
|
service:
|
||
|
|
main:
|
||
|
|
ports:
|
||
|
|
main:
|
||
|
|
protocol: http
|
||
|
|
targetPort: 80
|
||
|
|
port: 10687
|
||
|
|
|
||
|
|
fabulinus:
|
||
|
|
# cpu | gpu
|
||
|
|
device: cpu
|
||
|
|
model: "google/flan-t5-small"
|
||
|
|
# int8 | float16 | bfloat16 | int8_float16 | int8_bfloat16
|
||
|
|
quant_type: int8
|
||
|
|
max_batch_size: 32
|
||
|
|
disable_batching: true
|
||
|
|
|
||
|
|
workload:
|
||
|
|
main:
|
||
|
|
podSpec:
|
||
|
|
containers:
|
||
|
|
main:
|
||
|
|
imageSelector: image
|
||
|
|
probes:
|
||
|
|
liveness:
|
||
|
|
enabled: true
|
||
|
|
type: http
|
||
|
|
path: /docs
|
||
|
|
readiness:
|
||
|
|
enabled: true
|
||
|
|
type: http
|
||
|
|
path: /docs
|
||
|
|
startup:
|
||
|
|
enabled: true
|
||
|
|
type: tcp
|
||
|
|
env:
|
||
|
|
TAKEOFF_DEVICE: "{{ .Values.fabulinus.device }}"
|
||
|
|
TAKEOFF_MODEL_NAME: "{{ .Values.fabulinus.model }}"
|
||
|
|
TAKEOFF_QUANT_TYPE: "{{ .Values.fabulinus.quant_type }}"
|
||
|
|
TAKEOFF_MAX_BATCH_SIZE: "{{ .Values.fabulinus.max_batch_size }}"
|
||
|
|
TAKEOFF_DISABLE_BATCHING: "{{ .Values.fabulinus.disable_batching }}"
|
||
|
|
|
||
|
|
persistence:
|
||
|
|
models:
|
||
|
|
enabled: true
|
||
|
|
mountPath: "/code/models"
|
||
|
|
|
||
|
|
portal:
|
||
|
|
open:
|
||
|
|
enabled: true
|