mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-02 20:40:36 +00:00
make it work on gpus
This commit is contained in:
parent
ee96c4891b
commit
f99ca37f91
7 changed files with 30 additions and 21 deletions
|
@ -5,6 +5,7 @@ metadata:
|
|||
spec:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
storageClassName: gp2
|
||||
resources:
|
||||
requests:
|
||||
storage: 1Gi
|
||||
|
@ -25,9 +26,11 @@ spec:
|
|||
app.kubernetes.io/name: llama-stack
|
||||
app.kubernetes.io/component: server
|
||||
spec:
|
||||
nodeSelector:
|
||||
eks.amazonaws.com/nodegroup: cpu
|
||||
containers:
|
||||
- name: llama-stack
|
||||
image: llamastack/distribution-remote-vllm:latest
|
||||
image: llamastack/distribution-postgres-demo:latest
|
||||
imagePullPolicy: Always # since we have specified latest instead of a version
|
||||
env:
|
||||
- name: ENABLE_CHROMADB
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue