mirror of
https://github.com/wassname/vllm.git
synced 2026-09-12 13:01:01 +08:00
[Frontend] Refactor prompt processing (#4028)
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
co-authored by
Roger Wang
parent
89c1c6a196
commit
739b61a348
@@ -32,7 +32,10 @@ async def _async_serving_chat_init():
|
||||
model_config,
|
||||
served_model_names=[MODEL_NAME],
|
||||
response_role="assistant",
|
||||
chat_template=CHAT_TEMPLATE)
|
||||
chat_template=CHAT_TEMPLATE,
|
||||
lora_modules=None,
|
||||
prompt_adapters=None,
|
||||
request_logger=None)
|
||||
return serving_completion
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user