From b46ca01340dfc096e88147e4f9dd3f971708d635 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Wed, 30 Apr 2025 14:53:15 -0700
Subject: [PATCH] UI: Set max_updates_second to 12 by default

When the tokens/second at at ~50 and the model is a thinking model,
the markdown rendering for the streaming message becomes a CPU
bottleneck.
---
 modules/shared.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/shared.py b/modules/shared.py
index 4c1179e3..fb10c014 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -47,7 +47,7 @@ settings = {
     'max_new_tokens_max': 4096,
     'prompt_lookup_num_tokens': 0,
     'max_tokens_second': 0,
-    'max_updates_second': 0,
+    'max_updates_second': 12,
     'auto_max_new_tokens': True,
     'ban_eos_token': False,
     'add_bos_token': True,