vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Added support for . (any character) token in grammar engine. (#6467)

Browse source 
* Added support for . (any characer) token in grammar engine.

* Add integration tests for any-character symbol.
This commit is contained in:
Clint Herron 2024-06-06 06:08:52 -07:00 • committed by GitHub
parent a143c04375
commit ad675e1c67
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 52 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama.cpp
View file

@ -13640,7 +13640,7 @@ static std::pair<bool, const llama_grammar_element *> llama_grammar_match_char(
const uint32_t chr) {
bool found = false;
bool is_positive_char = pos->type == LLAMA_GRETYPE_CHAR;
bool is_positive_char = pos->type == LLAMA_GRETYPE_CHAR || pos->type == LLAMA_GRETYPE_CHAR_ANY;
GGML_ASSERT(is_positive_char || pos->type == LLAMA_GRETYPE_CHAR_NOT); // NOLINT
@ -13649,6 +13649,10 @@ static std::pair<bool, const llama_grammar_element *> llama_grammar_match_char(
// inclusive range, e.g. [a-z]
found = found || (pos->value <= chr && chr <= pos[1].value);
pos += 2;
} else if (pos->type == LLAMA_GRETYPE_CHAR_ANY) {
// Any character matches "."
found = true;
pos += 1;
} else {
// exact char match, e.g. [a] or "a"
found = found || pos->value == chr;
@ -13666,7 +13670,7 @@ static bool llama_grammar_match_partial_char(
const llama_grammar_element * pos,
const llama_partial_utf8 partial_utf8) {
bool is_positive_char = pos->type == LLAMA_GRETYPE_CHAR;
bool is_positive_char = pos->type == LLAMA_GRETYPE_CHAR || pos->type == LLAMA_GRETYPE_CHAR_ANY;
GGML_ASSERT(is_positive_char || pos->type == LLAMA_GRETYPE_CHAR_NOT);
uint32_t partial_value = partial_utf8.value;
@ -13696,6 +13700,9 @@ static bool llama_grammar_match_partial_char(
return is_positive_char;
}
pos += 2;
} else if (pos->type == LLAMA_GRETYPE_CHAR_ANY) {
// Any character matches "."
return true;
} else {
// exact char match, e.g. [a] or "a"
if (low <= pos->value && pos->value <= high) {
@ -13756,6 +13763,7 @@ static void llama_grammar_advance_stack(
}
case LLAMA_GRETYPE_CHAR:
case LLAMA_GRETYPE_CHAR_NOT:
case LLAMA_GRETYPE_CHAR_ANY:
if (std::find(new_stacks.begin(), new_stacks.end(), stack) == new_stacks.end()) {
// only add the stack if it's not a duplicate of one we already have
new_stacks.emplace_back(stack);