apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 16:22:57 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Doc] add chat_template_kwagrs and update params docs (#3103)

Browse Source 
* add chat_template_kwagrs and update params docs

* add chat_template_kwagrs and update params docs

* update enable_thinking

* pre-commit

* update test case

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
LiqinruiG
2025-07-31 19:44:06 +08:00
committed by GitHub
parent 22cab724e8
commit 25005fee30
11 changed files with 648 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
fastdeploy/entrypoints/openai/protocol.py
View File

@@ -343,28 +343,29 @@ class CompletionRequest(BaseModel):
suffix: Optional[dict] = None
temperature: Optional[float] = None
top_p: Optional[float] = None
top_k: Optional[int] = None
min_p: Optional[float] = None
include_stop_str_in_output: Optional[bool] = False
user: Optional[str] = None
# doc: begin-completion-sampling-params
top_k: Optional[int] = None
min_p: Optional[float] = None
repetition_penalty: Optional[float] = None
stop_token_ids: Optional[List[int]] = Field(default_factory=list)
min_tokens: Optional[int] = None
return_token_ids: Optional[bool] = None
max_streaming_response_tokens: Optional[int] = None
prompt_token_ids: Optional[List[int]] = None
include_stop_str_in_output: Optional[bool] = False
bad_words: Optional[List[str]] = None
# doc: end-completion-sampling-params
# doc: start-completion-extra-params
response_format: Optional[AnyResponseFormat] = None
guided_json: Optional[Union[str, dict, BaseModel]] = None
guided_regex: Optional[str] = None
guided_choice: Optional[list[str]] = None
guided_grammar: Optional[str] = None
# doc: begin-completion-sampling-params
repetition_penalty: Optional[float] = None
stop_token_ids: Optional[List[int]] = Field(default_factory=list)
# doc: end-completion-sampling-params
max_streaming_response_tokens: Optional[int] = None
return_token_ids: Optional[bool] = None
prompt_token_ids: Optional[List[int]] = None
# doc: end-completion-extra-params
def to_dict_for_infer(self, request_id=None, prompt=None):
"""
@@ -477,33 +478,34 @@ class ChatCompletionRequest(BaseModel):
stream_options: Optional[StreamOptions] = None
temperature: Optional[float] = None
top_p: Optional[float] = None
top_k: Optional[int] = None
min_p: Optional[float] = None
user: Optional[str] = None
metadata: Optional[dict] = None
response_format: Optional[AnyResponseFormat] = None
return_token_ids: Optional[bool] = None
prompt_token_ids: Optional[List[int]] = None
disable_chat_template: Optional[bool] = False
# doc: begin-chat-completion-sampling-params
top_k: Optional[int] = None
min_p: Optional[float] = None
min_tokens: Optional[int] = None
enable_thinking: Optional[bool] = None
reasoning_max_tokens: Optional[int] = None
max_streaming_response_tokens: Optional[int] = None
include_stop_str_in_output: Optional[bool] = False
bad_words: Optional[List[str]] = None
repetition_penalty: Optional[float] = None
stop_token_ids: Optional[List[int]] = Field(default_factory=list)
# doc: end-chat-completion-sampling-params
response_format: Optional[AnyResponseFormat] = None
# doc: start-completion-extra-params
chat_template_kwargs: Optional[dict] = None
reasoning_max_tokens: Optional[int] = None
structural_tag: Optional[str] = None
guided_json: Optional[Union[str, dict, BaseModel]] = None
guided_regex: Optional[str] = None
guided_choice: Optional[list[str]] = None
guided_grammar: Optional[str] = None
structural_tag: Optional[str] = None
# doc: begin-chat-completion-sampling-params
repetition_penalty: Optional[float] = None
stop_token_ids: Optional[List[int]] = Field(default_factory=list)
# doc: end-chat-completion-sampling-params
return_token_ids: Optional[bool] = None
prompt_token_ids: Optional[List[int]] = None
max_streaming_response_tokens: Optional[int] = None
disable_chat_template: Optional[bool] = False
# doc: end-chat-completion-extra-params
def to_dict_for_infer(self, request_id=None):
"""