furyhawk/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-07-21 10:15:35 +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
2026-02-03 07:57:17 +02:00
committed by GitHub
co-authored by firecoperana <firecoperana>
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
include/llama.h
+4 -69
View File
@@ -489,39 +489,7 @@ extern "C" {
// grammar types
struct llama_grammar;
// grammar element type
enum llama_gretype {
// end of rule definition
LLAMA_GRETYPE_END = 0,
// start of alternate definition for rule
LLAMA_GRETYPE_ALT = 1,
// non-terminal element: reference to rule
LLAMA_GRETYPE_RULE_REF = 2,
// terminal element: character (code point)
LLAMA_GRETYPE_CHAR = 3,
// inverse char(s) ([^a], [^a-b] [^abc])
LLAMA_GRETYPE_CHAR_NOT = 4,
// modifies a preceding LLAMA_GRETYPE_CHAR or LLAMA_GRETYPE_CHAR_ALT to
// be an inclusive range ([a-z])
LLAMA_GRETYPE_CHAR_RNG_UPPER = 5,
// modifies a preceding LLAMA_GRETYPE_CHAR or
// LLAMA_GRETYPE_CHAR_RNG_UPPER to add an alternate char to match ([ab], [a-zA])
LLAMA_GRETYPE_CHAR_ALT = 6,
// any character (.)
LLAMA_GRETYPE_CHAR_ANY = 7,
};
typedef struct llama_grammar_element {
enum llama_gretype type;
uint32_t value; // Unicode code point or rule ID
} llama_grammar_element;
// performance timing information
struct llama_timings {
@@ -1194,10 +1162,10 @@ extern "C" {
/// @param n_rules The number of rules.
/// @param start_rule_index The index of the root rule (the starting point of the grammar).
/// @return The initialized llama_grammar or nullptr if initialization failed.
LLAMA_API struct llama_grammar * llama_grammar_init(
const llama_grammar_element ** rules,
size_t n_rules,
size_t start_rule_index);
//LLAMA_API struct llama_grammar * llama_grammar_init(
// const llama_grammar_element ** rules,
// size_t n_rules,
// size_t start_rule_index);
struct llama_sampler_grammar;
LLAMA_API void llama_grammar_init_lazy(struct llama_sampler_grammar * grammar);
@@ -1489,39 +1457,6 @@ const std::vector<std::pair<std::string, struct ggml_tensor *>> & llama_internal
struct llama_context * ctx
);
struct llama_partial_utf8 {
uint32_t value; // bit value so far (unshifted)
int n_remain; // num bytes remaining; -1 indicates invalid sequence
};
struct llama_grammar_candidate {
size_t index;
const uint32_t * code_points;
llama_partial_utf8 partial_utf8;
};
using llama_grammar_rule = std::vector< llama_grammar_element>;
using llama_grammar_stack = std::vector<const llama_grammar_element *>;
using llama_grammar_rules = std::vector<llama_grammar_rule>;
using llama_grammar_stacks = std::vector<llama_grammar_stack>;
using llama_grammar_candidates = std::vector<llama_grammar_candidate>;
const llama_grammar_rules & llama_grammar_get_rules (const struct llama_grammar * grammar);
llama_grammar_stacks & llama_grammar_get_stacks( struct llama_grammar * grammar);
void llama_grammar_accept(struct llama_grammar* grammar, uint32_t chr);
std::vector<llama_grammar_candidate> llama_grammar_reject_candidates_for_stack(
const llama_grammar_rules & rules,
const llama_grammar_stack & stack,
const llama_grammar_candidates & candidates);
std::pair<std::vector<uint32_t>, llama_partial_utf8> decode_utf8(
const std::string & src,
llama_partial_utf8 partial_start);
// Randomly selects a token from the candidates based on their probabilities using given std::mt19937.
// This is a temporary workaround in order to fix race conditions when sampling with multiple sequences.