xgrammar

Grammar()

This class represents a grammar object in XGrammar, and can be used later in the grammar-guided generation.

• xgrammar.StructuralTagItem
  • StructuralTagItem
    • StructuralTagItem.begin
    • StructuralTagItem.end
    • StructuralTagItem.schema_

GrammarCompiler(tokenizer_info, *[, ...])	The compiler for grammars.
CompiledGrammar()	This is the primary object to store compiled grammar.
GrammarMatcher(compiled_grammar, *[, ...])	Match the output of the LLM to the specified grammar, then generate the mask for the next token.
TokenizerInfo(encoded_vocab[, vocab_type, ...])	The tokenizer info contains the vocabulary, the type of the vocabulary, and necessary information for the grammar-guided generation.
VocabType(value[, names, module, qualname, ...])	The type of the vocabulary.

• Bitmask Operations
  • allocate_token_bitmask()
  • apply_token_bitmask_inplace()
  • reset_token_bitmask()
  • get_bitmask_shape()
  • bitmask_dtype
• Recursion Depth Management
  • get_max_recursion_depth()
  • set_max_recursion_depth()
  • max_recursion_depth()