From 96f364def0b52d501ce8877b6769c2b673f6a98c Mon Sep 17 00:00:00 2001
From: Marco van Zijl <marco@mvzijl.nl>
Date: Tue, 2 Jun 2026 20:32:56 +0200
Subject: [PATCH] LiteLLM: added max_parallel_requests

---
 apps/litellm/values.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/apps/litellm/values.yaml b/apps/litellm/values.yaml
index d8a2137..eeae268 100644
--- a/apps/litellm/values.yaml
+++ b/apps/litellm/values.yaml
@@ -59,11 +59,13 @@ litellm:
         model_info:
           mode: chat
           max_input_tokens: 131072
+          max_parallel_requests: 1
       - model_name: qwen122
         litellm_params:
           model: openai/qwen122
           api_base: http://framework-llm.open-webui.svc.cluster.local:8080/v1
           api_key: not-needed
+          max_parallel_requests: 1
         model_info:
           mode: chat
           max_input_tokens: 262144
@@ -73,6 +75,7 @@ litellm:
           model: openai/qwen122-abliterated
           api_base: http://framework-llm.open-webui.svc.cluster.local:8080/v1
           api_key: not-needed
+          max_parallel_requests: 1
         model_info:
           mode: chat
           max_input_tokens: 262144