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

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

@@ -168,12 +168,8 @@ class OpenAIServingCompletion(OpenAIServing):
model_name = self._get_model_name(request.model, lora_request)
num_prompts = len(engine_prompts)
# Similar to the OpenAI API, when n != best_of, we do not stream the
# results. In addition, we do not stream the results when use
# beam search.
stream = (request.stream
and (request.best_of is None or request.n == request.best_of)
and not request.use_beam_search)
# We do not stream the results when use beam search.
stream = (request.stream and not request.use_beam_search)
# Streaming response
if stream: