Skip to content

Conversation

@dodekapod
Copy link
Contributor

llama-server treats an empty string as grammar and doesn't use the default grammar provided with --grammar-file on the command line ( see server.cpp ). This PR fixes --grammar-file parameter in llama-server by accepting only non-empty strings.

@dodekapod
Copy link
Contributor Author

@ngxson thank you for the approval. How to merge this now ?

@dodekapod dodekapod requested a review from ngxson March 14, 2025 10:12
@ngxson ngxson merged commit add2a3a into ggml-org:master Mar 14, 2025
47 checks passed
@dodekapod dodekapod deleted the fix_grammar_file_in_server branch March 14, 2025 10:27
jpohhhh pushed a commit to Telosnex/llama.cpp that referenced this pull request Mar 14, 2025
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Mar 19, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants