From ae131f1b0228532d92e4bec04545a9d8b970a294 Mon Sep 17 00:00:00 2001
From: jenkins <jenkins@bstein.dev>
Date: Mon, 29 Jun 2026 14:33:32 -0300
Subject: [PATCH] fix(ai): set ollama warm-model limits

---
 services/ai-llm/deployment.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/services/ai-llm/deployment.yaml b/services/ai-llm/deployment.yaml
index f413c0e3c..10000f6e1 100644
--- a/services/ai-llm/deployment.yaml
+++ b/services/ai-llm/deployment.yaml
@@ -71,6 +71,8 @@ spec:
               memory: 2Gi
               nvidia.com/gpu.shared: 1
             limits:
+              cpu: "2"
+              memory: 4Gi
               nvidia.com/gpu.shared: 1
       containers:
         - name: ollama