apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Cherry-Pick] Fix reasoning parser register name (#4795) (#4816)

Browse Source 
* [Feature] add a new reasoning parser (#4571)

* add new reasoning_parser initial commit

* add parser file content

* add register

* ernie_test_reasoning_parser

* support <tool_call> token and add tool_parser

* add and fix unit tests

* modify reasoning_parser

* modify reasoning parser and tool parser

* modify unit tests

* modify reasoning_parser and tool_parser

* modify unit tests

* fix tool_parser

* modify the logic of reasoning_parser and tool_parser

* add and modify unit tests

* standardize code style

* simplify reasoning_parser and tool_parser

* modify unit test

* [BugFix] Fix finish reason in _create_chat_completion_choice  (#4582)

* fix n_param _create_chat_completion_choicel

* fix unit test

* fix final_res

* modify unit tests

* [BugFix] fix offline llm chat "enable_thinking" is always "False" (#4686)

* fix enable_thinking

* recover ernie4_5_vl_processor

* fix parser register name (#4795)

Co-authored-by: luukunn <83932082+luukunn@users.noreply.github.com>

---------

Co-authored-by: luukunn <83932082+luukunn@users.noreply.github.com>
This commit is contained in:
kxz2002
2025-11-06 10:51:40 +08:00
committed by GitHub
parent 7e7a91855b
commit a218291831
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/models/ernie4_5_moe.py
View File

@@ -795,7 +795,7 @@ class Ernie4_5_MoePretrainedModel(PretrainedModel):
"""
get_tensor_parallel_mappings
"""
logger.info("erine inference model _get_tensor_parallel_mappings")
logger.info("ernie inference model _get_tensor_parallel_mappings")
from fastdeploy.model_executor.models.tp_utils import (
build_expanded_keys,
has_prefix,

2
fastdeploy/model_executor/models/ernie4_5_mtp.py
View File

@@ -63,7 +63,7 @@ class Ernie4_5_MTPPretrainedModel(PretrainedModel):
"""
get_tensor_parallel_mappings
"""
logger.info("erine inference model _get_tensor_parallel_mappings")
logger.info("ernie inference model _get_tensor_parallel_mappings")
from paddleformers.transformers.conversion_utils import split_or_merge_func

4
fastdeploy/reasoning/ernie_45_vl_thinking_reasoning_parser.py
View File

@@ -21,10 +21,10 @@ from fastdeploy.entrypoints.openai.protocol import ChatCompletionRequest, DeltaM
from fastdeploy.reasoning import ReasoningParser, ReasoningParserManager
@ReasoningParserManager.register_module("erine-45-vl-thinking")
@ReasoningParserManager.register_module("ernie-45-vl-thinking")
class Ernie45VLThinkingReasoningParser(ReasoningParser):
"""
Reasoning parser for ernir_vl model.
Reasoning parser for ernie_vl model.
The ernie_vl model uses ...</think>... tokens to denote reasoning text
within its output. The model provides a strict switch to disable reasoning

2
tests/entrypoints/openai/test_max_streaming_tokens.py
View File

@@ -532,7 +532,7 @@ class TestMaxStreamingResponseTokens(IsolatedAsyncioTestCase):
mock_processor_instance.process_response_chat = mock_process_response_chat
mock_processor_instance.enable_multimodal_content = Mock(return_value=False)
mock_processor_instance.reasoning_parser = Mock(__class__.__name__ == "ErineTestReasoningParser")
mock_processor_instance.reasoning_parser = Mock(__class__.__name__ == "Ernie45VLThinkingReasoningParser")
mock_processor_instance.data_processor = Mock(
process_response_dict=lambda resp, stream, enable_thinking, include_stop_str_in_output: resp
)