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

add custom server params (#1868)

Browse Source
This commit is contained in:
Roy
2023-12-04 04:59:18 +08:00
committed by GitHub
parent 0f90effc66
commit 60dc62dc9e
3 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -253,8 +253,10 @@ async def create_chat_completion(request: ChatCompletionRequest,
n=request.n,
presence_penalty=request.presence_penalty,
frequency_penalty=request.frequency_penalty,
repetition_penalty=request.repetition_penalty,
temperature=request.temperature,
top_p=request.top_p,
min_p=request.min_p,
stop=request.stop,
stop_token_ids=request.stop_token_ids,
max_tokens=request.max_tokens,
@@ -497,9 +499,11 @@ async def create_completion(request: CompletionRequest, raw_request: Request):
best_of=request.best_of,
presence_penalty=request.presence_penalty,
frequency_penalty=request.frequency_penalty,
repetition_penalty=request.repetition_penalty,
temperature=request.temperature,
top_p=request.top_p,
top_k=request.top_k,
min_p=request.min_p,
stop=request.stop,
stop_token_ids=request.stop_token_ids,
ignore_eos=request.ignore_eos,