jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
Files
0629696333ef554e512489a47d66688e6f446c79
GenAIExamples/CodeGen/kubernetes/manifests/gaudi/codegen.yaml
Lianhao Lu 0629696333 K8S manifest: Update ChatQnA/CodeGen/CodeTrans/DocSum 
- Update ChatQnA/CodeGen/CodeTrans/DocSum k8s manifest
  to avoid requiring creating directory for cache model.

- Add chatqna-guardrails manifest files.

- Fix bug #752 introduced by PR #669

Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>
2024-09-06 16:09:42 +08:00

363 lines
9.5 KiB
YAML
Raw Blame History

---
# Source: codegen/charts/llm-uservice/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: codegen-llm-uservice-config
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
data:
TGI_LLM_ENDPOINT: "http://codegen-tgi"
HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
HF_HOME: "/tmp/.cache/huggingface"
http_proxy: ""
https_proxy: ""
no_proxy: ""
LOGFLAG: ""
---
# Source: codegen/charts/tgi/templates/configmap.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
name: codegen-tgi-config
labels:
helm.sh/chart: tgi-1.0.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "2.1.0"
app.kubernetes.io/managed-by: Helm
data:
MODEL_ID: "meta-llama/CodeLlama-7b-hf"
PORT: "2080"
HF_TOKEN: "insert-your-huggingface-token-here"
http_proxy: ""
https_proxy: ""
no_proxy: ""
HABANA_LOGS: "/tmp/habana_logs"
NUMBA_CACHE_DIR: "/tmp"
HF_HOME: "/tmp/.cache/huggingface"
MAX_INPUT_LENGTH: "1024"
MAX_TOTAL_TOKENS: "2048"
---
# Source: codegen/charts/llm-uservice/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: codegen-llm-uservice
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 9000
targetPort: 9000
protocol: TCP
name: llm-uservice
selector:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
---
# Source: codegen/charts/tgi/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: codegen-tgi
labels:
helm.sh/chart: tgi-1.0.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "2.1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 80
targetPort: 2080
protocol: TCP
name: tgi
selector:
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
---
# Source: codegen/templates/service.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: Service
metadata:
name: codegen
labels:
helm.sh/chart: codegen-1.0.0
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- port: 7778
targetPort: 7778
protocol: TCP
name: codegen
selector:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
---
# Source: codegen/charts/llm-uservice/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: codegen-llm-uservice
labels:
helm.sh/chart: llm-uservice-1.0.0
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
template:
metadata:
labels:
app.kubernetes.io/name: llm-uservice
app.kubernetes.io/instance: codegen
spec:
securityContext:
{}
containers:
- name: codegen
envFrom:
- configMapRef:
name: codegen-llm-uservice-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: false
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/llm-tgi:latest"
imagePullPolicy: IfNotPresent
ports:
- name: llm-uservice
containerPort: 9000
protocol: TCP
volumeMounts:
- mountPath: /tmp
name: tmp
livenessProbe:
failureThreshold: 24
httpGet:
path: v1/health_check
port: llm-uservice
initialDelaySeconds: 5
periodSeconds: 5
readinessProbe:
httpGet:
path: v1/health_check
port: llm-uservice
initialDelaySeconds: 5
periodSeconds: 5
startupProbe:
failureThreshold: 120
httpGet:
path: v1/health_check
port: llm-uservice
initialDelaySeconds: 5
periodSeconds: 5
resources:
{}
volumes:
- name: tmp
emptyDir: {}
---
# Source: codegen/charts/tgi/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: codegen-tgi
labels:
helm.sh/chart: tgi-1.0.0
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "2.1.0"
app.kubernetes.io/managed-by: Helm
spec:
# use explicit replica counts only of HorizontalPodAutoscaler is disabled
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
template:
metadata:
labels:
app.kubernetes.io/name: tgi
app.kubernetes.io/instance: codegen
spec:
securityContext:
{}
containers:
- name: tgi
envFrom:
- configMapRef:
name: codegen-tgi-config
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/tgi-gaudi:2.0.1"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data
name: model-volume
- mountPath: /tmp
name: tmp
ports:
- name: http
containerPort: 2080
protocol: TCP
livenessProbe:
failureThreshold: 24
initialDelaySeconds: 5
periodSeconds: 5
tcpSocket:
port: http
readinessProbe:
initialDelaySeconds: 5
periodSeconds: 5
tcpSocket:
port: http
startupProbe:
failureThreshold: 120
initialDelaySeconds: 5
periodSeconds: 5
tcpSocket:
port: http
resources:
limits:
habana.ai/gaudi: 1
memory: 64Gi
hugepages-2Mi: 500Mi
volumes:
- name: model-volume
emptyDir: {}
- name: tmp
emptyDir: {}
---
# Source: codegen/templates/deployment.yaml
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
apiVersion: apps/v1
kind: Deployment
metadata:
name: codegen
labels:
helm.sh/chart: codegen-1.0.0
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
app.kubernetes.io/version: "v1.0"
app.kubernetes.io/managed-by: Helm
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
template:
metadata:
labels:
app.kubernetes.io/name: codegen
app.kubernetes.io/instance: codegen
spec:
securityContext:
null
containers:
- name: codegen
env:
- name: LLM_SERVICE_HOST_IP
value: codegen-llm-uservice
#- name: MEGA_SERVICE_PORT
# value: 7778
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsNonRoot: true
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "opea/codegen:latest"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /tmp
name: tmp
ports:
- name: codegen
containerPort: 7778
protocol: TCP
# startupProbe:
# httpGet:
# host: codegen-llm-uservice
# port: 9000
# path: /
# initialDelaySeconds: 5
# periodSeconds: 5
# failureThreshold: 120
# livenessProbe:
# httpGet:
# path: /
# port: 7778
# readinessProbe:
# httpGet:
# path: /
# port: 7778
resources:
null
volumes:
- name: tmp
emptyDir: {}
Reference in New Issue View Git Blame Copy Permalink