k8s/ollama.yaml (47 lines of code) (raw):
# Copyright 2024 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http:#www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
apiVersion: apps/v1
kind: Deployment
metadata:
name: ollama
spec:
selector:
matchLabels:
name: ollama
template:
metadata:
labels:
name: ollama
spec:
containers:
- name: ollama
image: us-docker.pkg.dev/backlogged-ai/llm/ollama:v1.0.0
ports:
- name: http
containerPort: 8080
protocol: TCP
resources:
requests:
cpu: "20"
memory: "80Gi"
ephemeral-storage: "100Gi"
nvidia.com/gpu: "2"
limits:
cpu: "20"
memory: "80Gi"
ephemeral-storage: "100Gi"
nvidia.com/gpu: "2"
nodeSelector:
cloud.google.com/gke-accelerator: nvidia-h100-80gb
cloud.google.com/gke-gpu-driver-version: latest
---
apiVersion: v1
kind: Service
metadata:
name: ollama-service
spec:
selector:
name: ollama
type: ClusterIP
ports:
- protocol: TCP
port: 8080
targetPort: 8080