phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-13 16:46:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs(kubernetes): add a more fleshed out example of a Demo Kubernetes cluster

Browse source
This commit is contained in:
Ashwin Bharambe 2025-06-01 14:25:54 -07:00
parent 31ce208bda
commit a36b0c5fe3
7 changed files with 593 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

22
docs/source/distributions/k8s/apply.sh Normal file
View file

@ -0,0 +1,22 @@
#!/bin/bash
export POSTGRES_USER=${POSTGRES_USER:-llamastack}
export POSTGRES_DB=${POSTGRES_DB:-llamastack}
export POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-llamastack}
export INFERENCE_MODEL=${INFERENCE_MODEL:-meta-llama/Llama-3.2-3B-Instruct}
export SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
set -euo pipefail
set -x
envsubst < ./vllm-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 apply -f stack-configmap.yaml
envsubst < ./stack-k8s.yaml.template | kubectl apply -f -