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

[Frontend] Allow return_tokens_as_token_ids to be passed as a request param (#14066)

Browse Source 
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
This commit is contained in:
Benjamin Chislett
2025-03-05 01:30:40 -05:00
committed by GitHub
parent dae9ec464c
commit 32985bed7c
4 changed files with 64 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/entrypoints/openai/protocol.py
View File

@@ -369,6 +369,12 @@ class ChatCompletionRequest(OpenAIBaseModel):
"arguments. For example: {'qualname': "
"'my_module.MyLogitsProcessor', 'args': [1, 2], 'kwargs': "
"{'param': 'value'}}."))
return_tokens_as_token_ids: Optional[bool] = Field(
default=None,
description=(
"If specified with 'logprobs', tokens are represented "
" as strings of the form 'token_id:{token_id}' so that tokens "
"that are not JSON-encodable can be identified."))
# doc: end-chat-completion-extra-params
@@ -739,6 +745,12 @@ class CompletionRequest(OpenAIBaseModel):
"arguments. For example: {'qualname': "
"'my_module.MyLogitsProcessor', 'args': [1, 2], 'kwargs': "
"{'param': 'value'}}."))
return_tokens_as_token_ids: Optional[bool] = Field(
default=None,
description=(
"If specified with 'logprobs', tokens are represented "
" as strings of the form 'token_id:{token_id}' so that tokens "
"that are not JSON-encodable can be identified."))
# doc: end-completion-extra-params