From 7826ff039887b067363b9285e5af8e011fae1854 Mon Sep 17 00:00:00 2001
From: SiriusClaw <siriusclaw@openclaw.ai>
Date: Sat, 18 Apr 2026 19:35:20 +0000
Subject: [PATCH] fix: adjust max-model-len and memory utilization for Venice

---
 apps/base/customer1/openclaw/vllm-gemma.yaml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/apps/base/customer1/openclaw/vllm-gemma.yaml b/apps/base/customer1/openclaw/vllm-gemma.yaml
index 67c0409..11c3a05 100644
--- a/apps/base/customer1/openclaw/vllm-gemma.yaml
+++ b/apps/base/customer1/openclaw/vllm-gemma.yaml
@@ -32,8 +32,10 @@ spec:
             - "--dtype"
             - "bfloat16"
             - "--max-model-len"
-            - "32768"
+            - "8192"
             - "--trust-remote-code"
+            - "--gpu-memory-utilization"
+            - "0.95"
           ports:
             - containerPort: 8000
           resources: