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

Change top_k to be disabled with 0 (still accept -1 for now) (#17773)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-09 11:01:49 +01:00
committed by GitHub
parent 5b2dcbf0b8
commit c6798baa9c
6 changed files with 14 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/entrypoints/openai/protocol.py
View File

@@ -409,7 +409,7 @@ class ChatCompletionRequest(OpenAIBaseModel):
"repetition_penalty": 1.0,
"temperature": 1.0,
"top_p": 1.0,
"top_k": -1,
"top_k": 0,
"min_p": 0.0,
}
@@ -853,7 +853,7 @@ class CompletionRequest(OpenAIBaseModel):
"repetition_penalty": 1.0,
"temperature": 1.0,
"top_p": 1.0,
"top_k": -1,
"top_k": 0,
"min_p": 0.0,
}
@@ -1679,7 +1679,7 @@ class TranscriptionRequest(OpenAIBaseModel):
"repetition_penalty": 1.0,
"temperature": 1.0,
"top_p": 1.0,
"top_k": -1,
"top_k": 0,
"min_p": 0.0,
}