Skip to content

[Bugfix] deepseek_r1_reasoning_parser put reason content in wrong field in certain edge case #13097

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 13, 2025
Merged

[Bugfix] deepseek_r1_reasoning_parser put reason content in wrong field in certain edge case #13097

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions tests/entrypoints/openai/reasoning_parsers/test_deepseekr1_reasoning_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,10 +24,10 @@
"reasoning_content": "This is a reasoning section",
"content": None,
}
NO_REASONING = {
NO_CONTENT = {
"output": "This is content",
"reasoning_content": None,
"content": "This is content",
"reasoning_content": "This is content",
"content": None,
}
NO_REASONING_STREAMING = {
"output": "This is a reasoning section",
Expand Down Expand Up @@ -98,8 +98,8 @@
),
pytest.param(
False,
NO_REASONING,
id="no_reasoning_token",
NO_CONTENT,
id="no_content_token",
),
pytest.param(
True,
Expand Down
2 changes: 1 addition & 1 deletion vllm/entrypoints/openai/reasoning_parsers/deepseek_r1_reasoning_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,7 +128,7 @@ def extract_reasoning_content(
# Thus we assume the reasoning content is always at the start.
# Ref https://huggingface.co/deepseek-ai/DeepSeek-R1/commit/8a58a132790c9935686eb97f042afa8013451c9f
if self.think_end_token not in model_output:
return None, model_output
return model_output, None
else:
# Add a start token if it's missing to keep compatibility.
if self.think_start_token not in model_output:
Expand Down