From 1fda6f1ba7359a49e98bd84993d5701b1fcc17ec Mon Sep 17 00:00:00 2001
From: Roger Wang <hey@rogerw.io>
Date: Tue, 30 Sep 2025 23:16:12 -0700
Subject: [PATCH] add

Signed-off-by: Roger Wang <hey@rogerw.io>
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 82a5997..eadb931 100755
--- a/README.md
+++ b/README.md
@@ -1028,7 +1028,7 @@ We highly recommend using vLLM for deployment and inference. All of our evaluati
 
 ```shell
 # Launch vLLM model server
-vllm serve rednote-hilab/dots.ocr --trust-remote-code --async-scheduling
+vllm serve rednote-hilab/dots.ocr --trust-remote-code --async-scheduling --gpu-memory-utilization 0.95
 
 # vLLM API Demo
 # See demo/demo_vllm.py for details on parameter and prompt settings that help achieve the best output quality.