louis_lifu
/
vllm
mirror of https://github.com/vllm-project/vllm
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] chat method add_generation_prompt param (#7734)

This commit is contained in:
Brian Li 2024-08-22 01:33:35 +08:00 committed by GitHub
parent 9b73a2f498
commit d3c002eadc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/entrypoints/llm.py
View File

@ -353,7 +353,7 @@ class LLM:
use_tqdm: bool = True,
lora_request: Optional[LoRARequest] = None,
chat_template: Optional[str] = None,
add_generation_template: bool = True,
add_generation_prompt: bool = True,
) -> List[RequestOutput]:
"""
Generates responses for chat messages.
@ -374,7 +374,7 @@ class LLM:
lora_request: LoRA request to use for generation, if any.
chat_template: The template to use for structuring the chat.
If not provided, the model's default chat template will be used.
add_generation_template: If True, adds a generation template
add_generation_prompt: If True, adds a generation template
to each message.
Returns:
@ -392,7 +392,7 @@ class LLM:
tokenizer,
conversations,
chat_template=chat_template,
add_generation_template=add_generation_template)
add_generation_prompt=add_generation_prompt)
return self.generate(
prompts,