apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[fix]update apply_chat_template (#4249)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details

Browse Source 
* [fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test

* fix

* [fix]update apply_chat_template (#4137)

* update apply_chat_template

* fix unittest

* fix unittest

* fix

* fix

* fix unit test

* fix

* fix unit test

* add unit test
This commit is contained in:
luukunn
2025-09-25 16:41:56 +08:00
committed by GitHub
parent 8fdb950e9f
commit aebe12a58d
10 changed files with 146 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

89
tests/utils/test_custom_chat_template.py
View File

@@ -3,15 +3,11 @@ import unittest
from pathlib import Path
from unittest.mock import AsyncMock, MagicMock, mock_open, patch
from fastdeploy.engine.request import Request
from fastdeploy.engine.sampling_params import SamplingParams
from fastdeploy.entrypoints.chat_utils import load_chat_template
from fastdeploy.entrypoints.llm import LLM
from fastdeploy.entrypoints.openai.protocol import ChatCompletionRequest
from fastdeploy.entrypoints.openai.serving_chat import OpenAIServingChat
from fastdeploy.input.ernie4_5_processor import Ernie4_5Processor
from fastdeploy.input.ernie4_5_vl_processor import Ernie4_5_VLProcessor
from fastdeploy.input.text_processor import DataProcessor
class TestLodChatTemplate(unittest.IsolatedAsyncioTestCase):
@@ -108,91 +104,6 @@ class TestLodChatTemplate(unittest.IsolatedAsyncioTestCase):
chat_completion = await self.chat_completion_handler.create_chat_completion(request)
self.assertEqual("hello", chat_completion["chat_template"])
@patch("fastdeploy.input.ernie4_5_vl_processor.Ernie4_5_VLProcessor.__init__")
def test_ernie4_5_vl_processor(self, mock_class):
mock_class.return_value = None
ernie4_5_vl_processor = Ernie4_5_VLProcessor()
mock_request = Request.from_dict({"request_id": "123"})
def mock_apply_default_parameters(request):
return request
def mock_process_request(request, max_model_len):
return request
ernie4_5_vl_processor._apply_default_parameters = mock_apply_default_parameters
ernie4_5_vl_processor.process_request_dict = mock_process_request
result = ernie4_5_vl_processor.process_request(mock_request, chat_template="hello")
self.assertEqual("hello", result.chat_template)
@patch("fastdeploy.input.text_processor.DataProcessor.__init__")
def test_text_processor_process_request(self, mock_class):
mock_class.return_value = None
text_processor = DataProcessor()
mock_request = Request.from_dict(
{"request_id": "123", "prompt": "hi", "max_tokens": 128, "temperature": 1, "top_p": 1}
)
def mock_apply_default_parameters(request):
return request
def mock_process_request(request, max_model_len):
return request
def mock_text2ids(text, max_model_len):
return [1]
text_processor._apply_default_parameters = mock_apply_default_parameters
text_processor.process_request_dict = mock_process_request
text_processor.text2ids = mock_text2ids
text_processor.eos_token_ids = [1]
result = text_processor.process_request(mock_request, chat_template="hello")
self.assertEqual("hello", result.chat_template)
@patch("fastdeploy.input.ernie4_5_processor.Ernie4_5Processor.__init__")
def test_ernie4_5_processor_process(self, mock_class):
mock_class.return_value = None
ernie4_5_processor = Ernie4_5Processor()
mock_request = Request.from_dict(
{"request_id": "123", "messages": ["hi"], "max_tokens": 128, "temperature": 1, "top_p": 1}
)
def mock_apply_default_parameters(request):
return request
def mock_process_request(request, max_model_len):
return request
def mock_messages2ids(text):
return [1]
ernie4_5_processor._apply_default_parameters = mock_apply_default_parameters
ernie4_5_processor.process_request_dict = mock_process_request
ernie4_5_processor.messages2ids = mock_messages2ids
ernie4_5_processor.eos_token_ids = [1]
ernie4_5_processor.reasoning_parser = MagicMock()
result = ernie4_5_processor.process_request(mock_request, chat_template="hello")
self.assertEqual("hello", result.chat_template)
@patch("fastdeploy.entrypoints.llm.LLM.__init__")
def test_llm_load(self, mock_class):
mock_class.return_value = None
llm = LLM()
llm.llm_engine = MagicMock()
llm.default_sampling_params = MagicMock()
llm.chat_template = "hello"
def mock_run_engine(req_ids, **kwargs):
return req_ids
def mock_add_request(**kwargs):
return kwargs.get("chat_template")
llm._run_engine = mock_run_engine
llm._add_request = mock_add_request
result = llm.chat(["hello"], sampling_params=SamplingParams(1))
self.assertEqual("hello", result)
@patch("fastdeploy.entrypoints.llm.LLM.__init__")
def test_llm(self, mock_class):
mock_class.return_value = None