thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

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

Browse source 
* grammar : add support for std::regex_search() with trigger patterns

* common : update hermes2 pro trigger to search instead of match

* common : use regex_search with anchoring for partial matching

* common : adjust regex partial tests to use new pattern

* grammar : check pattern directly instead of adding a type

* common : adjust existing patterns to match new semantics
This commit is contained in:
Aldehir Rojas 2026-01-03 16:02:43 -06:00 • committed by GitHub
parent c69c7ebc90
commit cef1d23c5a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 83 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

18
common/sampling.cpp
View file

@ -179,24 +179,30 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
#endif // LLAMA_USE_LLGUIDANCE
} else {
std::vector<std::string> trigger_patterns;
std::vector<std::string> patterns_anywhere;
std::vector<llama_token> trigger_tokens;
for (const auto & trigger : params.grammar_triggers) {
switch (trigger.type) {
case COMMON_GRAMMAR_TRIGGER_TYPE_WORD:
{
const auto & word = trigger.value;
patterns_anywhere.push_back(regex_escape(word));
trigger_patterns.push_back(regex_escape(word));
break;
}
case COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN:
{
patterns_anywhere.push_back(trigger.value);
trigger_patterns.push_back(trigger.value);
break;
}
case COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN_FULL:
{
trigger_patterns.push_back(trigger.value);
const auto & pattern = trigger.value;
std::string anchored = "^$";
if (!pattern.empty()) {
anchored = (pattern.front() != '^' ? "^" : "")
+ pattern
+ (pattern.back() != '$' ? "$" : "");
}
trigger_patterns.push_back(anchored);
break;
}
case COMMON_GRAMMAR_TRIGGER_TYPE_TOKEN:
@ -210,10 +216,6 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
}
}
if (!patterns_anywhere.empty()) {
trigger_patterns.push_back("^[\\s\\S]*?(" + string_join(patterns_anywhere, "|") + ")[\\s\\S]*");
}
std::vector<const char *> trigger_patterns_c;
trigger_patterns_c.reserve(trigger_patterns.size());
for (const auto & regex : trigger_patterns) {