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

Added include_stop_str_in_output and length_penalty parameters to OpenAI API (#2562)

Browse Source
This commit is contained in:
Federico Galatolo 2024-01-24 19:21:56 +01:00 committed by GitHub
parent 3209b49033
commit f1f6cc10c7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/entrypoints/openai/protocol.py
View File

@ -78,6 +78,8 @@ class ChatCompletionRequest(BaseModel):
echo: Optional[bool] = False echo: Optional[bool] = False
repetition_penalty: Optional[float] = 1.0 repetition_penalty: Optional[float] = 1.0
min_p: Optional[float] = 0.0 min_p: Optional[float] = 0.0
include_stop_str_in_output: Optional[bool] = False
length_penalty: Optional[float] = 1.0
def to_sampling_params(self) -> SamplingParams: def to_sampling_params(self) -> SamplingParams:
return SamplingParams( return SamplingParams(
@ -97,6 +99,8 @@ class ChatCompletionRequest(BaseModel):
use_beam_search=self.use_beam_search, use_beam_search=self.use_beam_search,
skip_special_tokens=self.skip_special_tokens, skip_special_tokens=self.skip_special_tokens,
spaces_between_special_tokens=self.spaces_between_special_tokens, spaces_between_special_tokens=self.spaces_between_special_tokens,
include_stop_str_in_output=self.include_stop_str_in_output,
length_penalty=self.length_penalty,
) )
@ -127,6 +131,8 @@ class CompletionRequest(BaseModel):
spaces_between_special_tokens: Optional[bool] = True spaces_between_special_tokens: Optional[bool] = True
repetition_penalty: Optional[float] = 1.0 repetition_penalty: Optional[float] = 1.0
min_p: Optional[float] = 0.0 min_p: Optional[float] = 0.0
include_stop_str_in_output: Optional[bool] = False
length_penalty: Optional[float] = 1.0
def to_sampling_params(self): def to_sampling_params(self):
echo_without_generation = self.echo and self.max_tokens == 0 echo_without_generation = self.echo and self.max_tokens == 0
@ -150,6 +156,8 @@ class CompletionRequest(BaseModel):
prompt_logprobs=self.logprobs if self.echo else None, prompt_logprobs=self.logprobs if self.echo else None,
skip_special_tokens=self.skip_special_tokens, skip_special_tokens=self.skip_special_tokens,
spaces_between_special_tokens=(self.spaces_between_special_tokens), spaces_between_special_tokens=(self.spaces_between_special_tokens),
include_stop_str_in_output=self.include_stop_str_in_output,
length_penalty=self.length_penalty,
) )