common, grammar: add recursive depth limit, make it a requirement (#31153)
* common, grammar: add recursive depth limit, make it a requirement * catch more recursive functions * common : tidy up peg parser changes * grammar : reject candidates in a loop, without a depth limit The depth limit in llama_grammar_reject_candidates_for_stack counted the code points of a vocab token, so any token of 256 chars or more was always rejected under a grammar, such as the 512-space token of GLM-4.7-Flash or the long space tokens of Laguna-S-2.1. The rejection now walks the code points with its own stack of levels instead of recursing: there is no limit and no stack risk, whatever the length of a token from the GGUF, and the masks match master. * grammar : track rejected candidates as indices into the input At a given code point a candidate only differs from its input by the position of its code point pointer, so the levels now carry indices into the input candidates instead of copies. The first level needs no special case and the rejects map back to the input directly. Grammar sampling gets faster than master on GLM-4.7, Laguna, Qwen3.6 and gemma-4 with the json, list and spaces grammars, same masks. * nit : shorten the comment of llama_grammar_reject_step * common : add depth_guard for schema walks * grammar : move GRAMMAR_RECURSIVE_LIMIT into the .cpp * common : reduce recursion limit for peg parser * improve --------- Co-authored-by: Alde Rojas <hello@alde.dev> Co-authored-by: Pascal <admin@serveurperso.com>
This commit is contained in:
21 files changed
+531
-212
No files matched your search
+27
-15
@@ -10,10 +10,12 @@
|
||||
#include <initializer_list>
|
||||
#include <map>
|
||||
#include <memory>
|
||||
#include <regex>
|
||||
#include <set>
|
||||
#include <stdexcept>
|
||||
|
||||
// The parser can run with a lower limit than COMMON_RECURSIVE_LIMIT
|
||||
static constexpr int RULE_RECURSIVE_LIMIT = 64;
|
||||
|
||||
// Trick to catch missing branches
|
||||
template <typename T>
|
||||
inline constexpr bool is_always_false_v = false;
|
||||
@@ -186,13 +188,17 @@ std::string common_peg_ast_node::sanitized_text() const {
|
||||
}
|
||||
|
||||
void common_peg_ast_arena::visit(common_peg_ast_id id, const common_peg_ast_visitor & visitor) const {
|
||||
if (id == COMMON_PEG_INVALID_AST_ID) {
|
||||
return;
|
||||
}
|
||||
const auto & node = get(id);
|
||||
visitor(node);
|
||||
for (const auto & child : node.children) {
|
||||
visit(child, visitor);
|
||||
// no recursion: the AST is several nodes deep per level of the input
|
||||
std::vector<common_peg_ast_id> stack = { id };
|
||||
while (!stack.empty()) {
|
||||
const auto cur = stack.back();
|
||||
stack.pop_back();
|
||||
if (cur == COMMON_PEG_INVALID_AST_ID) {
|
||||
continue;
|
||||
}
|
||||
const auto & node = get(cur);
|
||||
visitor(node);
|
||||
stack.insert(stack.end(), node.children.rbegin(), node.children.rend());
|
||||
}
|
||||
}
|
||||
|
||||
@@ -736,8 +742,15 @@ struct parser_executor {
|
||||
}
|
||||
|
||||
common_peg_parse_result operator()(const common_peg_rule_parser & p) {
|
||||
// only rules recurse, a recursive rule is entered once per input level
|
||||
if (ctx.rule_depth[p.child] >= RULE_RECURSIVE_LIMIT) {
|
||||
throw common_peg_recursion_error("input is nested more than " + std::to_string(RULE_RECURSIVE_LIMIT) + " levels deep");
|
||||
}
|
||||
|
||||
// Parse the child
|
||||
ctx.rule_depth[p.child]++;
|
||||
auto result = arena.parse(p.child, ctx, start_pos);
|
||||
ctx.rule_depth[p.child]--;
|
||||
|
||||
if (!result.fail()) {
|
||||
std::string_view text;
|
||||
@@ -819,6 +832,10 @@ common_peg_parse_result common_peg_arena::parse(common_peg_parse_context & ctx,
|
||||
if (root_ == COMMON_PEG_INVALID_PARSER_ID) {
|
||||
throw std::runtime_error("No root parser set");
|
||||
}
|
||||
|
||||
// Initialize rule depth for all parsers
|
||||
ctx.rule_depth.assign(parsers_.size(), 0);
|
||||
|
||||
return parse(root_, ctx, start);
|
||||
}
|
||||
|
||||
@@ -1069,11 +1086,6 @@ common_peg_parser operator|(const std::string & str, const common_peg_parser & p
|
||||
return operator|(str.c_str(), p);
|
||||
}
|
||||
|
||||
static std::string rule_name(const std::string & name) {
|
||||
static const std::regex invalid_rule_chars_re("[^a-zA-Z0-9-]+");
|
||||
return std::regex_replace(name, invalid_rule_chars_re, "-");
|
||||
}
|
||||
|
||||
common_peg_parser_builder::common_peg_parser_builder() {}
|
||||
|
||||
common_peg_parser common_peg_parser_builder::sequence(const std::vector<common_peg_parser_id> & parsers) {
|
||||
@@ -1155,14 +1167,14 @@ common_peg_parser common_peg_parser_builder::schema(const common_peg_parser & p,
|
||||
}
|
||||
|
||||
common_peg_parser common_peg_parser_builder::rule(const std::string & name, const common_peg_parser & p, bool trigger) {
|
||||
auto clean_name = rule_name(name);
|
||||
auto clean_name = gbnf_format_rule_name(name);
|
||||
auto rule_id = arena_.add_parser(common_peg_rule_parser{clean_name, p.id(), trigger});
|
||||
arena_.add_rule(clean_name, rule_id);
|
||||
return ref(clean_name);
|
||||
}
|
||||
|
||||
common_peg_parser common_peg_parser_builder::rule(const std::string & name, const std::function<common_peg_parser()> & builder_fn, bool trigger) {
|
||||
auto clean_name = rule_name(name);
|
||||
auto clean_name = gbnf_format_rule_name(name);
|
||||
if (arena_.has_rule(clean_name)) {
|
||||
return ref(clean_name);
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user