biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Deprecate best_of Sampling Parameter in anticipation for vLLM V1 (#13997)

Browse Source 
Signed-off-by: vincent-4 <vincentzhongy+githubvincent4@gmail.com>
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Vincent
2025-03-05 15:22:43 -05:00
committed by GitHub
parent a32c8669ca
commit a4f1ee35d6
12 changed files with 16 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/entrypoints/openai/protocol.py
View File

@@ -242,7 +242,6 @@ class ChatCompletionRequest(OpenAIBaseModel):
user: Optional[str] = None
# doc: begin-chat-completion-sampling-params
best_of: Optional[int] = None
use_beam_search: bool = False
top_k: Optional[int] = None
min_p: Optional[float] = None
@@ -479,7 +478,6 @@ class ChatCompletionRequest(OpenAIBaseModel):
return SamplingParams.from_optional(
n=self.n,
best_of=self.best_of,
presence_penalty=self.presence_penalty,
frequency_penalty=self.frequency_penalty,
repetition_penalty=repetition_penalty,
@@ -650,7 +648,6 @@ class CompletionRequest(OpenAIBaseModel):
# https://platform.openai.com/docs/api-reference/completions/create
model: Optional[str] = None
prompt: Union[list[int], list[list[int]], str, list[str]]
best_of: Optional[int] = None
echo: Optional[bool] = False
frequency_penalty: Optional[float] = 0.0
logit_bias: Optional[dict[str, float]] = None
@@ -848,7 +845,6 @@ class CompletionRequest(OpenAIBaseModel):
return SamplingParams.from_optional(
n=self.n,
best_of=self.best_of,
presence_penalty=self.presence_penalty,
frequency_penalty=self.frequency_penalty,
repetition_penalty=repetition_penalty,