diff --git a/clusters/k3s-dgx/apps/huihui-granite-inference.yaml b/clusters/k3s-dgx/apps/huihui-granite-inference.yaml index 114be8e..d0f98f3 100644 --- a/clusters/k3s-dgx/apps/huihui-granite-inference.yaml +++ b/clusters/k3s-dgx/apps/huihui-granite-inference.yaml @@ -4,16 +4,13 @@ metadata: name: huihui-granite spec: model: - modelFormat: - name: huggingface - storageUri: "hf://huihui-ai/Huihui-granite-4.1-30b-abliterated" + uri: hf://huihui-ai/Huihui-granite-4.1-30b-abliterated + name: huihui-ai/Huihui-granite-4.1-30b-abliterated replicas: 1 template: containers: - name: main image: quay.io/pierdipi/vllm-cpu:latest - args: - - --model_name=huihui-granite securityContext: runAsNonRoot: false env: