From d3fc86a43e2287e0446a4b3c9acf1300611f1f85 Mon Sep 17 00:00:00 2001
From: Haotian Liu <6631389+haotian-liu@users.noreply.github.com>
Date: Wed, 24 Jan 2024 14:23:27 -0600
Subject: [PATCH] Improve Chinese character streaming when the last char is
 half Chinese word. (#95)

---
 python/sglang/utils.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/python/sglang/utils.py b/python/sglang/utils.py
index ac103415e..dc4ea45b7 100644
--- a/python/sglang/utils.py
+++ b/python/sglang/utils.py
@@ -154,6 +154,9 @@ def find_printable_text(text):
     # If the last token is a CJK character, we print the characters.
     elif len(text) > 0 and _is_chinese_char(ord(text[-1])):
         return text
+    # Otherwise if the penultimate token is a CJK character, we print the characters except for the last one.
+    elif len(text) > 1 and _is_chinese_char(ord(text[-2])):
+        return text[:-1]
     # Otherwise, prints until the last space char (simple heuristic to avoid printing incomplete words,
     # which may change with the subsequent token -- there are probably smarter ways to do this!)
     else: