phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

first draft

Browse source
This commit is contained in:
Kai Wu 2025-07-25 10:41:06 -07:00
parent 025163d8e6
commit e614241876
9 changed files with 64 additions and 60 deletions
Download patch file Download diff file Expand all files Collapse all files

43
docs/source/distributions/k8s/apply.sh
View file

@ -13,6 +13,9 @@ export POSTGRES_PASSWORD=llamastack
export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
# Set USE_EBS to false if you don't have permission to use EKS EBS
export USE_EBS=${USE_EBS:-false}
# HF_TOKEN should be set by the user; base64 encode it for the secret
if [ -n "${HF_TOKEN:-}" ]; then
export HF_TOKEN_BASE64=$(echo -n "$HF_TOKEN" | base64)
@ -47,17 +50,37 @@ if [ -n "${HF_TOKEN:-}" ]; then
envsubst < ./hf-token-secret.yaml.template | kubectl apply -f -
fi
envsubst < ./vllm-k8s.yaml.template | kubectl apply -f -
envsubst < ./vllm-safety-k8s.yaml.template | kubectl apply -f -
envsubst < ./postgres-k8s.yaml.template | kubectl apply -f -
envsubst < ./chroma-k8s.yaml.template | kubectl apply -f -
# Apply templates with appropriate storage configuration based on USE_EBS setting
if [ "$USE_EBS" = "true" ]; then
echo "Using EBS storage for persistent volumes"
envsubst < ./vllm-k8s.yaml.template | kubectl apply -f -
envsubst < ./vllm-safety-k8s.yaml.template | kubectl apply -f -
envsubst < ./postgres-k8s.yaml.template | kubectl apply -f -
envsubst < ./chroma-k8s.yaml.template | kubectl apply -f -
kubectl create configmap llama-stack-config --from-file=stack_run_config.yaml \
--dry-run=client -o yaml > stack-configmap.yaml
kubectl create configmap llama-stack-config --from-file=stack_run_config.yaml \
--dry-run=client -o yaml > stack-configmap.yaml
kubectl apply -f stack-configmap.yaml
kubectl apply -f stack-configmap.yaml
envsubst < ./stack-k8s.yaml.template | kubectl apply -f -
envsubst < ./ingress-k8s.yaml.template | kubectl apply -f -
envsubst < ./stack-k8s.yaml.template | kubectl apply -f -
envsubst < ./ingress-k8s.yaml.template | kubectl apply -f -
envsubst < ./ui-k8s.yaml.template | kubectl apply -f -
else
echo "Using emptyDir for storage (data will not persist across pod restarts)"
# Process templates to replace EBS storage with emptyDir
envsubst < ./vllm-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f -
envsubst < ./vllm-safety-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f -
envsubst < ./postgres-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f -
envsubst < ./chroma-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f -
envsubst < ./ui-k8s.yaml.template | kubectl apply -f -
kubectl create configmap llama-stack-config --from-file=stack_run_config.yaml \
--dry-run=client -o yaml > stack-configmap.yaml
kubectl apply -f stack-configmap.yaml
# Apply the same emptyDir transformation to the remaining templates
envsubst < ./stack-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f -
envsubst < ./ingress-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f -
envsubst < ./ui-k8s.yaml.template | sed 's/persistentVolumeClaim:/emptyDir: {}/g' | sed '/claimName:/d' | kubectl apply -f -
fi