minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Use allow auto truncate in the OpenAI API endpoint (#15369)

Browse Source
This commit is contained in:
Kangyan-Zhou
2025-12-25 18:45:57 -08:00
committed by GitHub
parent 0271fc3456
commit a91e072f33
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/entrypoints/openai/serving_chat.py
+1 -1
View File
@@ -133,7 +133,7 @@ class OpenAIServingChat(OpenAIServingBase):
max_output_tokens max_output_tokens
and server_context_length and server_context_length
and max_output_tokens > server_context_length and max_output_tokens > server_context_length
): ) and not self.tokenizer_manager.server_args.allow_auto_truncate:
return ( return (
f"max_completion_tokens is too large: {max_output_tokens}." f"max_completion_tokens is too large: {max_output_tokens}."
f"This model supports at most {server_context_length} completion tokens." f"This model supports at most {server_context_length} completion tokens."