phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-13 00:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

make it work on gpus

Browse source
This commit is contained in:
Raghotham Murthy 2025-06-24 12:20:04 -07:00
parent ee96c4891b
commit f99ca37f91
7 changed files with 30 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/source/distributions/k8s/apply.sh
View file

@ -16,6 +16,14 @@ export SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
set -euo pipefail
set -x
# Install NVIDIA device plugin for GPU support
echo "Installing NVIDIA device plugin..."
kubectl apply -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/refs/tags/v0.17.2/deployments/static/nvidia-device-plugin.yml
# Wait for NVIDIA device plugin to be ready
echo "Waiting for NVIDIA device plugin to be ready..."
kubectl wait --for=condition=ready pod -l name=nvidia-device-plugin-ds -n kube-system --timeout=300s
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 -