[Optimization] The pre- and post-processing pipeline do not perform dict conversion (#5494)

* to_request_for_infer initial commit * refact to from_chat_completion_request * preprocess use request initial commit * bugfix * processors refact to using request * bug fix * refact Request from_generic_request * post process initial commit * bugfix * postprocess second commit * bugfix * serving_embedding initial commit * serving_reward initial commit * bugfix * replace function name * async_llm initial commit * offline initial commit and fix bug * bugfix * fix async_llm * remove add speculate_metrics into data * fix logprobs bug * fix echo bug * fix bug * fix reasoning_max_tokens * bugfix * bugfix and modify unittest * bugfix and modify unit test * bugfix * bugfix * bugfix * modify unittest * fix error when reasong_content is none for text_processor * remove some unnessary logic * revert removed logic * implement add and set method for RequestOutput and refact code * modify unit test * modify unit test * union process_request and process_request_obj * remove a unit test * union process_response and process_response_obj * support qwen3_vl_processor * modify unittest and remove comments * fix prompt_logprobs * fix codestyle * add v1 * v1 * fix unit test * fix unit test * fix pre-commit * fix * add process request * add process request * fix * fix * fix unit test * fix unit test * fix unit test * fix unit test * fix unit test * remove file * add unit test * add unit test * add unit test * fix unit test * fix unit test * fix * fix --------- Co-authored-by: Jiaxin Sui <95567040+plusNew001@users.noreply.github.com> Co-authored-by: luukunn <981429396@qq.com> Co-authored-by: luukunn <83932082+luukunn@users.noreply.github.com> Co-authored-by: Zhang Yulong <35552275+ZhangYulongg@users.noreply.github.com>
2026-04-24 01:29:57 +08:00 · 2026-01-22 00:50:52 +08:00
parent fe5ba4b509
commit 6e416c62dd
66 changed files with 16614 additions and 739 deletions
@@ -321,10 +321,12 @@ class Ernie4_5Processor(BaseDataProcessor):
            if token_ids[-1] == self.tokenizer.eos_token_id:
                token_ids = token_ids[:-1]
        delta_text, _, previous_texts = self.ids2tokens(token_ids, req_id)
+        response_dict["outputs"]["enable_parser"] = False
        if is_end:
            full_text = previous_texts + delta_text
            response_dict["outputs"]["text"] = full_text
            if self.reasoning_parser:
+                response_dict["outputs"]["enable_parser"] = True
                reasoning_content, text = self.reasoning_parser.extract_reasoning_content(
                    full_text,
                    response_dict,
@@ -335,6 +337,7 @@ class Ernie4_5Processor(BaseDataProcessor):
                reasoning_tokens = self.tokenizer.tokenize(reasoning_content)
                response_dict["outputs"]["reasoning_token_num"] = len(reasoning_tokens)
            if self.tool_parser_obj:
+                response_dict["outputs"]["enable_parser"] = True
                tool_parser = self.tool_parser_obj(self.tokenizer)
                tool_call_info = tool_parser.extract_tool_calls(full_text, response_dict)
                if tool_call_info.tools_called:
@@ -360,6 +363,7 @@ class Ernie4_5Processor(BaseDataProcessor):
        is_end = response_dict["finished"]
        req_id = response_dict["request_id"]
        token_ids = response_dict["outputs"]["token_ids"]
+        response_dict["outputs"]["enable_parser"] = False

        if is_end and len(token_ids) > 0 and not kwargs.get("include_stop_str_in_output"):
            if token_ids[-1] == self.tokenizer.eos_token_id:
@@ -376,6 +380,7 @@ class Ernie4_5Processor(BaseDataProcessor):
                token_ids,
                self.model_status_dict[req_id],
            )
+            response_dict["outputs"]["enable_parser"] = True
            response_dict["outputs"]["delta_message"] = reasoning_delta_message
            reasoning_content = reasoning_delta_message.reasoning_content if reasoning_delta_message else None
            reasoning_tokens = self.tokenizer.tokenize(reasoning_content) if reasoning_content else []
@@ -389,6 +394,7 @@ class Ernie4_5Processor(BaseDataProcessor):
        else:
            response_dict["outputs"]["text"] = delta_text
        if self.tool_parser_obj:
+            response_dict["outputs"]["enable_parser"] = True
            if req_id not in self.tool_parser_dict:
                self.tool_parser_dict[req_id] = self.tool_parser_obj(self.tokenizer)
            tool_parser = self.tool_parser_dict[req_id]