apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

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

Browse Source 
* 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>
This commit is contained in:
kxz2002
2026-01-22 00:50:52 +08:00
committed by GitHub
parent fe5ba4b509
commit 6e416c62dd
66 changed files with 16614 additions and 739 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/entrypoints/openai/serving_completion.py
+8 -5
View File
@@ -27,7 +27,7 @@ import numpy as np
import fastdeploy.envs as envs
import fastdeploy.metrics.trace as tracing
from fastdeploy.engine.request import RequestOutput
from fastdeploy.engine.request import Request, RequestOutput
from fastdeploy.entrypoints.openai.protocol import (
CompletionLogprobs,
CompletionRequest,
@@ -178,8 +178,11 @@ class OpenAIServingCompletion:
try:
for idx, prompt in enumerate(request_prompts):
request_id_idx = f"{request_id}_{idx}"
current_req_dict = request.to_dict_for_infer(request_id_idx, prompt)
current_req_dict["arrival_time"] = time.time()
if not envs.ENABLE_V1_DATA_PROCESSOR:
current_req_dict = request.to_dict_for_infer(request_id_idx, prompt)
else:
current_req_dict = Request.from_generic_request(request, request_id=f"{request_id}_0")
current_req_dict["metrics"]["arrival_time"] = time.time()
prompt_token_ids = await self.engine_client.format_and_add_data(current_req_dict) # tokenize
if isinstance(prompt_token_ids, np.ndarray):
prompt_token_ids = prompt_token_ids.tolist()
@@ -562,7 +565,7 @@ class OpenAIServingCompletion:
draft_logprobs=draft_logprobs_res,
speculate_metrics=output_speculate_metrics,
)
if not res["finished"] and "delta_message" in output:
if not res["finished"] and output["enable_parser"]:
delta_message_output = output["delta_message"]
if delta_message_output is None:
continue
@@ -737,7 +740,7 @@ class OpenAIServingCompletion:
else None
),
reasoning_content=output.get("reasoning_content"),
tool_calls=output.get("tool_call"),
tool_calls=output.get("tool_call", None),
logprobs=aggregated_logprobs,
draft_logprobs=aggregated_draft_logprobs,
prompt_logprobs=clamp_prompt_logprobs(prompt_logprobs_res),