From 7fa2dfefa23a92a00a36519283ccc1ee597f7f2e Mon Sep 17 00:00:00 2001
From: lbenhorin <lbenhorin@nvidia.com>
Date: Fri, 3 Jul 2026 15:34:48 +0300
Subject: [PATCH] docs(groot): add note on inference.queue_threshold value for
 stable inference

---
 docs/source/groot.mdx | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/docs/source/groot.mdx b/docs/source/groot.mdx
index 831f42d08..13f19f8bf 100644
--- a/docs/source/groot.mdx
+++ b/docs/source/groot.mdx
@@ -216,6 +216,9 @@ uv run lerobot-rollout \
   --inference.queue_threshold=0
 ```
 
+> [!NOTE]
+> Value of `inference.queue_threshold` should not exeed 0.5 to ensure stable inference.
+
 ## License
 
 GR00T N1.7 is released under the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/).