add detoken switch (#5463)

docs/online_serving/README.md

@@ -223,6 +223,9 @@ include_draft_logprobs: Optional[bool] = False
 # Whether to return log probabilities during draft stages (e.g., pre-generation or intermediate steps)
 # for debugging or analysis of the generation process (default False means not returned).
 
+include_logprobs_decode_token: Optional[bool] = True
+# Whether to include decoded token in the logprobs/prompt_logprobs results, (default True means the decoded token is always include in results).
+
 logits_processors_args: Optional[Dict] = None
 # Additional arguments for logits processors, enabling customization of generation logic
 # (e.g., dynamically adjusting probability distributions).
@@ -481,6 +484,9 @@ include_draft_logprobs: Optional[bool] = False
 # Whether to return log probabilities during draft stages (e.g., pre-generation or intermediate steps)
 # for debugging or analysis of the generation process (default False means not returned).
 
+include_logprobs_decode_token: Optional[bool] = True
+# Whether to include decoded token in the prompt_logprobs results, (default True means the decoded token is always include in results).
+
 logits_processors_args: Optional[Dict] = None
 # Additional arguments for logits processors, enabling customization of generation logic
 # (e.g., dynamically adjusting probability distributions).

docs/zh/online_serving/README.md

@@ -218,6 +218,9 @@ top_p_normalized_logprobs: Optional[bool] = False
 include_draft_logprobs: Optional[bool] = False
 # 是否在预生成或中间步骤返回对数概率（log probabilities），用于调试或分析生成过程（默认 False 表示不返回）。
 
+include_logprobs_decode_token: Optional[bool] = True
+# 是否在logprobs/prompt_logprobs结果中返回解码后的token，（默认的True表示总是在结果中返回）
+
 logits_processors_args: Optional[Dict] = None
 # 传递给 logits 处理器（logits processors）的额外参数，用于自定义生成过程中的逻辑（如动态调整概率分布）。
 
@@ -469,6 +472,9 @@ top_p_normalized_logprobs: Optional[bool] = False
 include_draft_logprobs: Optional[bool] = False
 # 是否在预生成或中间步骤返回对数概率（log probabilities），用于调试或分析生成过程（默认 False 表示不返回）。
 
+include_logprobs_decode_token: Optional[bool] = True
+# 是否在prompt_logprobs结果中返回解码后的token，（默认的True表示总是在结果中返回）
+
 logits_processors_args: Optional[Dict] = None
 # 传递给 logits 处理器（logits processors）的额外参数，用于自定义生成过程中的逻辑（如动态调整概率分布）。