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

3
vllm/entrypoints/openai/api_server.py
View File

@@ -1745,6 +1745,7 @@ async def init_app_state(
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
trust_request_chat_template=args.trust_request_chat_template,
log_error_stack=args.log_error_stack,
) if "encode" in supported_tasks else None
state.openai_serving_embedding = OpenAIServingEmbedding(
@@ -1754,6 +1755,7 @@ async def init_app_state(
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
trust_request_chat_template=args.trust_request_chat_template,
log_error_stack=args.log_error_stack,
) if "embed" in supported_tasks else None
state.openai_serving_classification = ServingClassification(
@@ -1777,6 +1779,7 @@ async def init_app_state(
request_logger=request_logger,
chat_template=resolved_chat_template,
chat_template_content_format=args.chat_template_content_format,
trust_request_chat_template=args.trust_request_chat_template,
log_error_stack=args.log_error_stack,
)
state.openai_serving_transcription = OpenAIServingTranscription(