mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-24 13:25:01 +08:00
[Bugfix] Improve GLM4 MoE Reasoning Parser's is_reasoning_end Condition (#25355)
Signed-off-by: frankwang28 <frank.wbb@hotmail.com> Signed-off-by: Frank Wang <41319051+frankwang28@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Chauncey <chaunceyjiang@gmail.com> Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Frank Wang
yewentao256
parent
8c1b61bd77
commit
f16c440c9f
203
tests/reasoning/test_glm4_moe_reasoning_parser.py
Normal file
203
tests/reasoning/test_glm4_moe_reasoning_parser.py
Normal file
@ -0,0 +1,203 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import pytest
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
from tests.reasoning.utils import run_reasoning_extraction
|
||||
from vllm.reasoning import ReasoningParser, ReasoningParserManager
|
||||
|
||||
parser_name = "glm45"
|
||||
start_token = "<think>"
|
||||
end_token = "</think>"
|
||||
|
||||
REASONING_MODEL_NAME = "zai-org/GLM-4.5"
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def glm45_tokenizer():
|
||||
return AutoTokenizer.from_pretrained(REASONING_MODEL_NAME)
|
||||
|
||||
|
||||
WITH_THINK = {
|
||||
"output": "<think>This is a reasoning section</think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
|
||||
WITH_THINK_STREAM = {
|
||||
"output": "<think>This is a reasoning section</think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
|
||||
WITHOUT_THINK = {
|
||||
"output": "This is the rest",
|
||||
"reasoning_content": None,
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
|
||||
WITHOUT_THINK_STREAM = {
|
||||
"output": "This is the rest",
|
||||
"reasoning_content": None,
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
|
||||
COMPLETE_REASONING = {
|
||||
"output": "<think>This is a reasoning section</think>",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
MULTILINE_REASONING = {
|
||||
"output":
|
||||
"<think>This is a reasoning\nsection</think>This is the rest\nThat",
|
||||
"reasoning_content": "This is a reasoning\nsection",
|
||||
"content": "This is the rest\nThat",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
ONLY_OPEN_TAG = {
|
||||
"output": "<think>This is a reasoning section",
|
||||
"reasoning_content": None,
|
||||
"content": "<think>This is a reasoning section",
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
|
||||
ONLY_OPEN_TAG_STREAM = {
|
||||
"output": "<think>This is a reasoning section",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
|
||||
TEST_CASES = [
|
||||
pytest.param(
|
||||
False,
|
||||
WITH_THINK,
|
||||
id="with_think",
|
||||
),
|
||||
pytest.param(
|
||||
True,
|
||||
WITH_THINK_STREAM,
|
||||
id="with_think_stream",
|
||||
),
|
||||
pytest.param(
|
||||
False,
|
||||
WITHOUT_THINK,
|
||||
id="without_think",
|
||||
),
|
||||
pytest.param(
|
||||
True,
|
||||
WITHOUT_THINK_STREAM,
|
||||
id="without_think_stream",
|
||||
),
|
||||
pytest.param(
|
||||
False,
|
||||
COMPLETE_REASONING,
|
||||
id="complete_reasoning",
|
||||
),
|
||||
pytest.param(
|
||||
True,
|
||||
COMPLETE_REASONING,
|
||||
id="complete_reasoning_stream",
|
||||
),
|
||||
pytest.param(
|
||||
False,
|
||||
MULTILINE_REASONING,
|
||||
id="multiline_reasoning",
|
||||
),
|
||||
pytest.param(
|
||||
True,
|
||||
MULTILINE_REASONING,
|
||||
id="multiline_reasoning_stream",
|
||||
),
|
||||
pytest.param(
|
||||
False,
|
||||
ONLY_OPEN_TAG,
|
||||
id="only_open_tag",
|
||||
),
|
||||
pytest.param(
|
||||
True,
|
||||
ONLY_OPEN_TAG_STREAM,
|
||||
id="only_open_tag_stream",
|
||||
),
|
||||
]
|
||||
|
||||
STILL_REASONING_PROMPT = """[gMASK]<sop><|system|>
|
||||
You are a helpful assistant.<|user|>
|
||||
What is the capital of France?<|assistant|>
|
||||
<think>The user is asking for the capital of"""
|
||||
|
||||
DONE_REASONING_PROMPT = """[gMASK]<sop><|system|>
|
||||
You are a helpful assistant.<|user|>
|
||||
What is the capital of France?<|assistant|>
|
||||
<think>The user is asking for the capital of France.</think>
|
||||
The capital of France is Paris."""
|
||||
|
||||
MULTI_TURN_STILL_REASONING_PROMPT = """[gMASK]<sop><|system|>
|
||||
You are a helpful assistant.<|user|>
|
||||
What is the capital of France?<|assistant|>
|
||||
<think></think>
|
||||
The capital of France is Paris.<|user|>
|
||||
What about Chile?<|assistant|>
|
||||
<think>The user is asking for the capital of"""
|
||||
|
||||
MULTI_TURN_DONE_REASONING_PROMPT = """[gMASK]<sop><|system|>
|
||||
You are a helpful assistant.<|user|>
|
||||
What is the capital of France?<|assistant|>
|
||||
<think></think>
|
||||
The capital of France is Paris.<|user|>
|
||||
What about Chile?<|assistant|>
|
||||
<think>The user is asking for the capital of Chile.</think>
|
||||
The capital of Chile is Santiago."""
|
||||
|
||||
REASONING_END_TEST_CASES = [
|
||||
pytest.param(STILL_REASONING_PROMPT, False, id="still_reasoning"),
|
||||
pytest.param(DONE_REASONING_PROMPT, True, id="done_reasoning"),
|
||||
pytest.param(MULTI_TURN_STILL_REASONING_PROMPT,
|
||||
False,
|
||||
id="multi_turn_still_reasoning"),
|
||||
pytest.param(MULTI_TURN_DONE_REASONING_PROMPT,
|
||||
True,
|
||||
id="multi_turn_done_reasoning")
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("streaming, param_dict", TEST_CASES)
|
||||
def test_reasoning(
|
||||
streaming: bool,
|
||||
param_dict: dict,
|
||||
glm45_tokenizer,
|
||||
):
|
||||
output = glm45_tokenizer.tokenize(param_dict["output"])
|
||||
output_tokens: list[str] = [
|
||||
glm45_tokenizer.convert_tokens_to_string([token]) for token in output
|
||||
]
|
||||
parser: ReasoningParser = ReasoningParserManager.get_reasoning_parser(
|
||||
parser_name)(glm45_tokenizer)
|
||||
|
||||
reasoning, content = run_reasoning_extraction(parser,
|
||||
output_tokens,
|
||||
streaming=streaming)
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
output_ids = glm45_tokenizer.convert_tokens_to_ids(output)
|
||||
is_reasoning_end = parser.is_reasoning_end(output_ids)
|
||||
assert is_reasoning_end == param_dict["is_reasoning_end"]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("prompt, is_reasoning_end", REASONING_END_TEST_CASES)
|
||||
def test_is_reasoning_end_full_prompt(prompt: str, is_reasoning_end: bool,
|
||||
glm45_tokenizer):
|
||||
parser: ReasoningParser = ReasoningParserManager.get_reasoning_parser(
|
||||
parser_name)(glm45_tokenizer)
|
||||
tokens = glm45_tokenizer.tokenize(prompt)
|
||||
token_ids = glm45_tokenizer.convert_tokens_to_ids(tokens)
|
||||
check_is_reasoning_end = parser.is_reasoning_end(token_ids)
|
||||
assert check_is_reasoning_end == is_reasoning_end
|
||||
@ -30,6 +30,7 @@ class Glm4MoeModelReasoningParser(ReasoningParser):
|
||||
super().__init__(tokenizer, *args, **kwargs)
|
||||
self.think_start_token = "<think>"
|
||||
self.think_end_token = "</think>"
|
||||
self.assistant_token = "<|assistant|>"
|
||||
|
||||
if not self.model_tokenizer:
|
||||
raise ValueError(
|
||||
@ -38,14 +39,26 @@ class Glm4MoeModelReasoningParser(ReasoningParser):
|
||||
|
||||
self.think_start_token_id = self.vocab.get(self.think_start_token)
|
||||
self.think_end_token_id = self.vocab.get(self.think_end_token)
|
||||
self.assistant_token_id = self.vocab.get(self.assistant_token)
|
||||
if (self.think_start_token_id is None
|
||||
or self.think_end_token_id is None):
|
||||
or self.think_end_token_id is None
|
||||
or self.assistant_token_id is None):
|
||||
raise RuntimeError(
|
||||
"Glm4MoeModel reasoning parser could not locate "
|
||||
"think start/end tokens in the tokenizer!")
|
||||
"think start/end or assistant tokens in the tokenizer!")
|
||||
|
||||
def is_reasoning_end(self, input_ids: list[int]) -> bool:
|
||||
return self.think_end_token_id in input_ids
|
||||
"""
|
||||
GLM's chat template has <think></think> tokens after every
|
||||
<|assistant|> token. Thus, we need to check if </think> is
|
||||
after the most recent <|assistant|> token (if present).
|
||||
"""
|
||||
for token_id in input_ids[::-1]:
|
||||
if token_id == self.think_end_token_id:
|
||||
return True
|
||||
elif token_id == self.assistant_token_id:
|
||||
return False
|
||||
return False
|
||||
|
||||
def extract_content_ids(self, input_ids: list[int]) -> list[int]:
|
||||
"""
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user