mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-10 06:45:01 +08:00
Support allowed_token_ids in ChatCompletionRequest (#19143)
Signed-off-by: Xu Song <xusong.vip@gmail.com>
This commit is contained in:
parent
b61dc5f972
commit
3da2313d78
@ -271,6 +271,7 @@ class ChatCompletionRequest(OpenAIBaseModel):
|
|||||||
spaces_between_special_tokens: bool = True
|
spaces_between_special_tokens: bool = True
|
||||||
truncate_prompt_tokens: Optional[Annotated[int, Field(ge=1)]] = None
|
truncate_prompt_tokens: Optional[Annotated[int, Field(ge=1)]] = None
|
||||||
prompt_logprobs: Optional[int] = None
|
prompt_logprobs: Optional[int] = None
|
||||||
|
allowed_token_ids: Optional[list[int]] = None
|
||||||
# --8<-- [end:chat-completion-sampling-params]
|
# --8<-- [end:chat-completion-sampling-params]
|
||||||
|
|
||||||
# --8<-- [start:chat-completion-extra-params]
|
# --8<-- [start:chat-completion-extra-params]
|
||||||
@ -549,6 +550,7 @@ class ChatCompletionRequest(OpenAIBaseModel):
|
|||||||
else RequestOutputKind.FINAL_ONLY,
|
else RequestOutputKind.FINAL_ONLY,
|
||||||
guided_decoding=guided_decoding,
|
guided_decoding=guided_decoding,
|
||||||
logit_bias=self.logit_bias,
|
logit_bias=self.logit_bias,
|
||||||
|
allowed_token_ids=self.allowed_token_ids,
|
||||||
extra_args=({"kv_transfer_params": self.kv_transfer_params}
|
extra_args=({"kv_transfer_params": self.kv_transfer_params}
|
||||||
if self.kv_transfer_params else None))
|
if self.kv_transfer_params else None))
|
||||||
|
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user