biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI] Reorganize scoring tests (#38207)

Browse Source 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-03-26 20:07:01 +08:00
committed by GitHub
parent f2d16207c7
commit dcdc145893
20 changed files with 1595 additions and 975 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/entrypoints/openai/engine/serving.py
View File

@@ -461,7 +461,7 @@ class OpenAIServing:
return self.create_error_response(
"truncate_prompt_tokens value is "
"greater than max_model_len."
" Please, select a smaller truncation size."
" Please request a smaller truncation size."
)
return None
@@ -724,7 +724,7 @@ class OpenAIServing:
f"This model's maximum context length is "
f"{max_model_len} tokens. However, you requested "
f"{token_num} tokens in the input for {operation}. "
f"Please reduce the length of the input.",
f"Please reduce the length of the input prompt.",
parameter="input_tokens",
value=token_num,
)