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

[Frontend] Cache chat template kwargs resolution (#26227)

Browse Source 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Isotr0py
2025-10-04 23:32:30 +08:00
committed by GitHub
parent 5c057e068f
commit a42d2df75f
7 changed files with 81 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
vllm/entrypoints/openai/serving_chat.py
View File

@@ -222,16 +222,14 @@ class OpenAIServingChat(OpenAIServing):
if not self.use_harmony:
# Common case.
request_chat_template = request.chat_template
chat_template_kwargs = request.chat_template_kwargs
if not self.trust_request_chat_template and (
request_chat_template is not None or
(chat_template_kwargs and
chat_template_kwargs.get("chat_template") is not None)):
return self.create_error_response(
"Chat template is passed with request, but "
"--trust-request-chat-template is not set. "
"Refused request with untrusted chat template.")
error_check_ret = self._validate_chat_template(
request_chat_template=request.chat_template,
chat_template_kwargs=request.chat_template_kwargs,
trust_request_chat_template=self.
trust_request_chat_template,
)
if error_check_ret is not None:
return error_check_ret
(
conversation,
request_prompts,
@@ -240,7 +238,7 @@ class OpenAIServingChat(OpenAIServing):
request,
tokenizer,
request.messages,
chat_template=request_chat_template or self.chat_template,
chat_template=request.chat_template or self.chat_template,
chat_template_content_format=self.
chat_template_content_format,
add_generation_prompt=request.add_generation_prompt,