From 596b5cb4d7d66f01605e57cccc0e4dd9e597365f Mon Sep 17 00:00:00 2001
From: Story Crater Bot <19826264+Riotpiaole@users.noreply.github.com>
Date: Wed, 19 Aug 2026 15:16:46 -0700
Subject: [PATCH] fix(llm-serving): bump reasoning memory limit to 36Gi
 headroom

---
 k8s/apps/llm-serving/reasoning.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/k8s/apps/llm-serving/reasoning.yaml b/k8s/apps/llm-serving/reasoning.yaml
index 353bff0..c14febf 100644
--- a/k8s/apps/llm-serving/reasoning.yaml
+++ b/k8s/apps/llm-serving/reasoning.yaml
@@ -79,7 +79,7 @@ spec:
       resources:
         limits:
           cpu: '16'
-          memory: 24Gi
+          memory: 36Gi
           nvidia.com/gpu: '1'
         requests:
           cpu: '8'