From ee5939eef34f9be75e190caa8d5b546d04e06785 Mon Sep 17 00:00:00 2001
From: HaimKortovich <haimkortovich88@gmail.com>
Date: Tue, 5 May 2026 13:31:20 -0500
Subject: [PATCH] test qwen

---
 .../apps/huihui-granite-inference.yaml        | 20 +++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/clusters/k3s-dgx/apps/huihui-granite-inference.yaml b/clusters/k3s-dgx/apps/huihui-granite-inference.yaml
index bad3c46..9a77c59 100644
--- a/clusters/k3s-dgx/apps/huihui-granite-inference.yaml
+++ b/clusters/k3s-dgx/apps/huihui-granite-inference.yaml
@@ -1,7 +1,7 @@
-apiVersion: serving.kserve.io/v1beta1
-kind: InferenceService
+apiVersion: "serving.kserve.io/v1beta1"
+kind: "InferenceService"
 metadata:
-  name: huihui-granite
+  name: "qwen-llm"
   namespace: kserve
 spec:
   predictor:
@@ -9,14 +9,14 @@ spec:
       modelFormat:
         name: huggingface
       args:
-        - --model_name=huihui-granite
-      storageUri: "hf://huihui-ai/Huihui-granite-4.1-30b-abliterated"
+        - --model_name=qwen
+      storageUri: "hf://Qwen/Qwen2.5-0.5B-Instruct"
       resources:
         limits:
-          cpu: "4"
-          memory: 16Gi
+          cpu: "2"
+          memory: 6Gi
           nvidia.com/gpu: "1"
         requests:
-          cpu: "2"
-          memory: 8Gi
-          nvidia.com/gpu: "1"
\ No newline at end of file
+          cpu: "1"
+          memory: 4Gi
+          nvidia.com/gpu: "1"