From 1a4e73b755ced3f695baae847c6b9fa46edbfdda Mon Sep 17 00:00:00 2001
From: HaimKortovich <haimkortovich88@gmail.com>
Date: Thu, 7 May 2026 14:59:55 -0500
Subject: [PATCH] use vlmm openai

---
 clusters/k3s-dgx/nim-service/qwen.yaml | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/clusters/k3s-dgx/nim-service/qwen.yaml b/clusters/k3s-dgx/nim-service/qwen.yaml
index 4d02000..ee491cd 100644
--- a/clusters/k3s-dgx/nim-service/qwen.yaml
+++ b/clusters/k3s-dgx/nim-service/qwen.yaml
@@ -60,11 +60,9 @@ spec:
     - "--enable-prefix-caching"
     - '--speculative-config={"method":"mtp","num_speculative_tokens":2}'
   image:
-    repository: nvcr.io/nim/nvidia/llm-nim
-    tag: "1.12"
+    repository: vllm/vllm-openai
+    tag: "v0.19.1-cu130"
     pullPolicy: IfNotPresent
-    pullSecrets:
-      - ngc-secret
   authSecret: hf-api-secret
   storage:
     nimCache: