diff --git a/docs/online_serving/README.md b/docs/online_serving/README.md index 178393489e..c00b62e318 100644 --- a/docs/online_serving/README.md +++ b/docs/online_serving/README.md @@ -192,9 +192,6 @@ return_token_ids: Optional[bool] = None prompt_token_ids: Optional[List[int]] = None # Directly passes the token ID list of the prompt, skipping the text encoding step (default None means using text input). -max_streaming_response_tokens: Optional[int] = None -# Maximum number of tokens returned at a time during streaming output (default None means no limit). - disable_chat_template: Optional[bool] = False # Whether to disable chat template rendering, using raw input directly (default False means template is enabled). @@ -369,9 +366,6 @@ return_token_ids: Optional[bool] = None prompt_token_ids: Optional[List[int]] = None # Directly passes the token ID list of the prompt, skipping the text encoding step (default None means using text input). - -max_streaming_response_tokens: Optional[int] = None -# Maximum number of tokens returned at a time during streaming output (default None means no limit). ``` ### Overview of Return Parameters diff --git a/docs/zh/online_serving/README.md b/docs/zh/online_serving/README.md index 5e72dd5ed4..250c24b37f 100644 --- a/docs/zh/online_serving/README.md +++ b/docs/zh/online_serving/README.md @@ -191,9 +191,6 @@ return_token_ids: Optional[bool] = None prompt_token_ids: Optional[List[int]] = None # 直接传入 prompt 的 token ID 列表,跳过文本编码步骤(默认 None 表示使用文本输入)。 -max_streaming_response_tokens: Optional[int] = None -# 流式输出时每次返回的最大 token 数(默认 None 表示不限制)。 - disable_chat_template: Optional[bool] = False # 是否禁用聊天模板渲染,直接使用原始输入(默认 False 表示启用模板)。 @@ -365,8 +362,6 @@ return_token_ids: Optional[bool] = None prompt_token_ids: Optional[List[int]] = None # 直接传入 prompt 的 token ID 列表,跳过文本编码步骤(默认 None 表示使用文本输入)。 -max_streaming_response_tokens: Optional[int] = None -# 流式输出时每次返回的最大 token 数(默认 None 表示不限制)。 ``` ### 返回参数总览