highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 10:57:36 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama: remove model loading for grammar (#10096)

Browse Source
This commit is contained in:
Parth Sareen
2025-04-24 11:51:19 -07:00
committed by GitHub
parent 40b10eee6d
commit a53d744b01
13 changed files with 521 additions and 107 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
llama/sampling_ext.h vendored
View File

@@ -35,8 +35,12 @@ extern "C"
int schema_to_grammar(const char *json_schema, char *grammar, size_t max_len);
struct llama_vocab * llama_load_vocab_from_file(const char * fname);
void llama_free_vocab(struct llama_vocab * vocab);
struct llama_grammar *grammar_init(char* grammar, uint32_t* tokens, size_t n_tokens, const char** pieces, uint32_t* eog_tokens, size_t n_eog_tokens);
void grammar_free(struct llama_grammar *g);
void grammar_apply(struct llama_grammar *g, struct llama_token_data_array *tokens);
void grammar_accept(struct llama_grammar *g, llama_token id);
#ifdef __cplusplus
}