Skip to content

Add grammar fields to GenerationConfig for constrained decoding #19616

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
meta-codesync merged 1 commit into from
May 15, 2026
+8 −0
Merged

Add grammar fields to GenerationConfig for constrained decoding #19616

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
8 changes: 8 additions & 0 deletions extension/llm/runner/irunner.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,14 @@ struct GenerationConfig {
// Whether to echo the input prompt in the output
bool echo = true;

// Grammar definition for constrained decoding (e.g. a JSON schema, regex,
// Lark CFG, or GBNF grammar). Empty string means no constraint.
std::string grammar;

// Grammar format: "json_schema", "regex", "lark", or "gbnf".
// Only used when grammar is non-empty.
std::string grammar_type;
Comment on lines +38 to +42
Comment on lines +38 to +42

// Whether to ignore EOS token and continue generating until max_new_tokens
bool ignore_eos = false;

Expand Down
Loading