Skip to content
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.

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

Support running multiple bash commands and compile in one query #736

Merged
merged 9 commits into from
Dec 15, 2024

Conversation

DonggeLiu
Copy link
Collaborator

No description provided.

@DonggeLiu
Copy link
Collaborator Author

/gcbrun exp -n dg -ag

@DonggeLiu
Copy link
Collaborator Author

DonggeLiu commented Dec 2, 2024

Reports:
https://llm-exp.oss-fuzz.com/Result-reports/scheduled/2024-11-30-weekly-all-2/
https://llm-exp.oss-fuzz.com/Result-reports/scheduled/2024-12-02-weekly-all-3/

Part of the lower performance of all-3 is due to GKE timeout.
As a result, 24 benchmarks' statuses are 'Running', with 12 of them had 0 build rate.

@@ -63,6 +62,11 @@ def _parse_tag(self, response: str, tag: str) -> str:
match = re.search(rf'<{tag}>(.*?)</{tag}>', response, re.DOTALL)
return match.group(1).strip() if match else ''

def _parse_tags(self, response: str, tag: str) -> list[str]:
"""Parses the XML-style tags from LLM response."""
matches = re.findall(rf'<{tag}>(.*?)</{tag}>', response, re.DOTALL)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For future work: Should we experiment with JSON formatting at some point? Let's create an issue if so.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done: #743

@DonggeLiu
Copy link
Collaborator Author

/gcbrun exp -n dg -ag

@DonggeLiu
Copy link
Collaborator Author

@DonggeLiu
Copy link
Collaborator Author

/gcbrun exp -n dg -ag

1 similar comment
@DonggeLiu
Copy link
Collaborator Author

/gcbrun exp -n dg -ag

@DonggeLiu
Copy link
Collaborator Author

The report looks good: 28/38
https://llm-exp.oss-fuzz.com/Result-reports/ofg-pr/2024-12-13-736-dg-comparison/index.html

I will remove the libdwarf benchmark set, which was used for testing only.

@DonggeLiu
Copy link
Collaborator Author

/gcbrun skip

@DonggeLiu DonggeLiu merged commit f871736 into main Dec 15, 2024
5 checks passed
@DonggeLiu DonggeLiu deleted the multi-commands branch December 15, 2024 23:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants