phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-26 22:18:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

adhoc, test, rm storage class

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-07-08 15:54:20 -07:00 • committed by Eric Huang
parent 83c89265e0
commit 2f51129495
9 changed files with 100 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

13
docs/source/distributions/k8s/apply.sh
View file

@ -13,9 +13,22 @@ export POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-llamastack}
export INFERENCE_MODEL=${INFERENCE_MODEL:-meta-llama/Llama-3.2-3B-Instruct}
export SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
# HF_TOKEN should be set by the user; base64 encode it for the secret
if [ -n "${HF_TOKEN:-}" ]; then
export HF_TOKEN_BASE64=$(echo -n "$HF_TOKEN" | base64)
else
echo "ERROR: HF_TOKEN not set. You need it for vLLM to download models from Hugging Face."
exit 1
fi
set -euo pipefail
set -x
# Apply the HF token secret if HF_TOKEN is provided
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 -