ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-23 14:44:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : add token matching support to llama-grammar (#1220)

Browse Source 
* llama : add token matching support to llama-grammar

llama : add token matching support to llama-grammar (#17816)

common/grammar : replace problematic backtracking regex `[\s\S]*` (#18342)

* disable tests and fix warnings

---------

Co-authored-by: firecoperana <firecoperana>
This commit is contained in:
firecoperana
2026-02-02 23:57:17 -06:00
committed by GitHub
parent 8ba7e2b40c
commit 7e8d444033
21 changed files with 644 additions and 916 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
src/llama.cpp
View File

@@ -7611,36 +7611,13 @@ int32_t llama_chat_builtin_templates(const char ** output, size_t len) {
// grammar
//
struct llama_grammar * llama_grammar_init(
const llama_grammar_element ** rules,
size_t n_rules,
size_t start_rule_index) {
return llama_grammar_init_impl(rules, n_rules, start_rule_index);
}
void llama_grammar_free(struct llama_grammar * grammar) {
llama_grammar_free_impl(grammar);
}
//
//void llama_grammar_init_lazy(struct llama_sampler* smpl) {
//
// if (!grammar) {
// return;
// }
// std::vector<const char*> trigger_patterns_c;
// trigger_patterns_c.reserve(grammar.grammar->trigger_patterns.size());
// for (auto& trigger_pattern : grammar.grammar->trigger_patterns) {
// trigger_patterns_c.push_back(trigger_pattern.pattern.c_str());
// }
// //auto* grammar_new = llama_grammar_init_impl(grammar->vocab, "", "root",
// // grammar->lazy, trigger_patterns_c.data(), trigger_patterns_c.size(),
// // grammar->trigger_tokens.data(), grammar->trigger_tokens.size());
//
//}
struct llama_grammar * llama_grammar_copy(const struct llama_grammar * grammar) {
return llama_grammar_copy_impl(grammar);
return llama_grammar_clone_impl(*grammar);
}
void llama_grammar_sample(
@@ -7661,7 +7638,7 @@ void llama_grammar_accept_token(
struct llama_grammar * grammar,
struct llama_context * ctx,
llama_token token) {
llama_grammar_accept_token_impl(grammar, &ctx->model.vocab, &ctx->sampling, token);
llama_grammar_accept_impl(*grammar, &ctx->model.vocab, &ctx->sampling, token);
}
//