[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>
2026-04-23 08:21:53 +08:00 · 2026-01-22 00:50:52 +08:00
parent fe5ba4b509
commit 6e416c62dd
66 changed files with 16614 additions and 739 deletions
@@ -15,17 +15,20 @@
 """

 import base64
+import time
 from collections.abc import AsyncGenerator
 from typing import Literal, Union

 import numpy as np
 from typing_extensions import assert_never, override

+import fastdeploy.envs as envs
 from fastdeploy.engine.pooling_params import PoolingParams
 from fastdeploy.engine.request import (
    EmbeddingOutput,
    EmbeddingRequestOutput,
    PoolingRequestOutput,
+    Request,
 )
 from fastdeploy.entrypoints.openai.protocol import (
    EmbeddingCompletionRequest,
@@ -66,12 +69,25 @@ class OpenAIServingEmbedding(ZmqOpenAIServing):
    @override
    def _request_to_dict(self, ctx: ServeContext):
        request: EmbeddingRequest = ctx.request
-        request_dict = super()._request_to_dict(ctx)
-        if hasattr(request, "to_pooling_params"):
-            pooling_params: PoolingParams = request.to_pooling_params()
-            pooling_params.verify("embed", self.cfg.model_config)
-            request_dict["pooling_params"] = pooling_params.to_dict()
-        return request_dict
+        if not envs.ENABLE_V1_DATA_PROCESSOR:
+            request_dict = super()._request_to_dict(ctx)
+            if hasattr(request, "to_pooling_params"):
+                pooling_params: PoolingParams = request.to_pooling_params()
+                pooling_params.verify("embed", self.cfg.model_config)
+                request_dict["pooling_params"] = pooling_params.to_dict()
+                request_dict["metrics"] = {}
+            return request_dict
+        else:
+            request_obj = None
+            if hasattr(request, "to_pooling_params"):
+                pooling_params: PoolingParams = request.to_pooling_params()
+                pooling_params.verify("embed", self.cfg.model_config)
+                request_obj = Request.from_generic_request(
+                    req=request, request_id=ctx.request_id, pooling_params=pooling_params
+                )
+                request_obj.metrics.arrival_time = time.time()
+                super()._process_chat_template_kwargs(request_obj)
+            return request_obj

    @override
    def _request_to_batch_dicts(self, ctx: ServeContext):