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

[Bugfix] chat method add_generation_prompt param (#7734)

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