happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604) 

* grammar: add test case for nullable symbol loop

Reproduce stack overflow (or OOM) with ( [x]* )* found while adding
GBNF support to ripgrep-edit.

llama-server reproducer:

curl \
  -X POST \
  -d '{
    "messages": [{ "role": "user", "content": "write yes" }],
    "grammar": "root ::= ( [x]* )*"
  }' \
  -H "Content-Type: application/json" \
  http://localhost:8811/v1/chat/completions

* grammar: prevent stack overflow with nullable symbol loop

Fix a potential stack overflow in llama_grammar_advance_stack that
could occur when processing grammars with nullable symbols that lead
to infinite derivations of empty strings. The fix introduces cycle
detection by tracking visited stacks to prevent infinite recursion.

rg-edit regexp: llama_grammar_advance_stack
rg-edit extra-args: -A20
rg-edit directive: """Rewrite: fix the following segfault:

[..]
⚫ Testing segfault. Grammar:
            root ::= ( [x]* )*

            root ::= ( [x]* )*

Segmentation fault         build/bin/test-grammar-integration"""

gptel-context:
(("~/llama.cpp/src/llama-grammar.cpp")
 ("~/llama.cpp/tests/test-grammar-integration.cpp")
 ("~/llama.cpp/grammars/./list.gbnf")
 ("~/llama.cpp/grammars/./json_arr.gbnf")
 ("~/llama.cpp/grammars/./json.gbnf")
 ("~/llama.cpp/grammars/./japanese.gbnf")
 ("~/llama.cpp/grammars/./english.gbnf")
 ("~/llama.cpp/grammars/./chess.gbnf")
 ("~/llama.cpp/grammars/./c.gbnf")
 ("~/llama.cpp/grammars/./arithmetic.gbnf")
 ("~/llama.cpp/grammars/./README.md"))

* grammar: convert recursive llama_grammar_advance_stack to iterative

This change converts the function to an iterative approach using
explicit stacks, which prevents deep recursion and eliminates the risk
of stack overflow.

rg-edit regexp: llama_grammar_advance_stack
rg-edit extra-args: -A30
rg-edit directive: """Rewrite: fix the following segfault:

[..]
⚫ Testing segfault. Grammar:
            root ::= ( [x]* )*

            root ::= ( [x]* )*

Segmentation fault         build/bin/test-grammar-integration

convert from recursive to interactive"""

gptel-context:
(("~/llama.cpp/src/llama-grammar.cpp")
 ("~/llama.cpp/tests/test-grammar-integration.cpp")
 ("~/llama.cpp/grammars/./list.gbnf")
 ("~/llama.cpp/grammars/./json_arr.gbnf")
 ("~/llama.cpp/grammars/./json.gbnf")
 ("~/llama.cpp/grammars/./japanese.gbnf")
 ("~/llama.cpp/grammars/./english.gbnf")
 ("~/llama.cpp/grammars/./chess.gbnf")
 ("~/llama.cpp/grammars/./c.gbnf")
 ("~/llama.cpp/grammars/./arithmetic.gbnf")
 ("~/llama.cpp/grammars/./README.md"))

v2: Added a `std::set` to perform tree-based lookups with O(N log N)
complexity. Testing with a parallel run of `test-grammar-integration`
shows a double-digit percentage increase in runtime. An
`unordered_set` with O(1) hashing was also evaluated, but the overhead
of constructing hash keys from pointers made it significantly slower
than the rbtree implementation that only requires an ordering
operator. The performance regression in the test suite appears
justified by the overall reduction in algorithmic complexity.

Co-developed-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>

* grammar: add test case for hang in repetition grammar processing

This commit adds a new test case to the grammar integration tests that
specifically targets a hang scenario in the repetition grammar parser
found while adding GBNF support to ripgrep-edit.

llama-server reproducer:

curl \
  -X POST \
  -d '{
    "messages": [{ "role": "user", "content": "write yes" }],
    "grammar": "root ::= (([^x]*){0,99}){0,99}"
  }' \
  -H "Content-Type: application/json" \
  http://localhost:8811/v1/chat/completions

* grammar: add repetition threshold check

The change introduces a maximum repetition threshold to avoid
excessive rule expansion during grammar parsing. When parsing
repetition patterns like {m,n}, the parser now calculates the
potential number of rules that would be generated and throws an error
if the product of previous rules and new rules exceeds the threshold.

A test case was added to verify the threshold is properly enforced for
deeply nested repetition patterns that would otherwise cause hangs.
This commit is contained in:
Andrea Arcangeli 2026-03-21 13:43:35 -04:00 committed by GitHub
parent 212f4521b0
commit 990e4d9698
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 118 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

74
src/llama-grammar.cpp
View File

@ -7,6 +7,7 @@
#include <cmath>
#include <algorithm>
#include <cstdint>
#include <set>
#include <stdexcept>
#define MAX_REPETITION_THRESHOLD 2000
@ -454,6 +455,7 @@ const char * llama_grammar_parser::parse_sequence(
bool is_nested) {
size_t last_sym_start = rule.size();
const char * pos = src;
uint64_t n_prev_rules = 1;
// use UINT64_MAX as the empty value because we aligned to the proper uint64_t type so -1 can't be used
// (though it's technically the same as -1 now)
@ -481,6 +483,18 @@ const char * llama_grammar_parser::parse_sequence(
// S' ::= S |
llama_grammar_rule prev_rule(rule.begin() + last_sym_start, rule.end());
// Calculate the total number of rules that will be generated by this repetition
uint64_t total_rules = 1; // Start with 1 for the original rule
if (!no_max && max_times > 0) {
total_rules = max_times;
} else if (min_times > 0) {
total_rules = min_times;
}
if (n_prev_rules * total_rules >= MAX_REPETITION_THRESHOLD) {
throw std::runtime_error("number of rules that are going to be repeated multiplied by the new repetition exceeds sane defaults, please reduce the number of repetitions or rule complexity");
}
if (min_times == 0) {
rule.resize(last_sym_start);
} else {
@ -508,12 +522,15 @@ const char * llama_grammar_parser::parse_sequence(
if (n_opt > 0) {
rule.push_back({LLAMA_GRETYPE_RULE_REF, last_rec_rule_id});
}
n_prev_rules *= total_rules;
GGML_ASSERT(n_prev_rules >= 1);
};
while (*pos) {
if (*pos == '"') { // literal string
pos++;
last_sym_start = rule.size();
n_prev_rules = 1;
while (*pos != '"') {
if (!*pos) {
throw std::runtime_error("unexpected end of input");
@ -531,6 +548,7 @@ const char * llama_grammar_parser::parse_sequence(
start_type = LLAMA_GRETYPE_CHAR_NOT;
}
last_sym_start = rule.size();
n_prev_rules = 1;
while (*pos != ']') {
if (!*pos) {
throw std::runtime_error("unexpected end of input");
@ -561,6 +579,7 @@ const char * llama_grammar_parser::parse_sequence(
auto token_pair = parse_token(vocab, pos);
const char * token_end = token_pair.second;
last_sym_start = rule.size();
n_prev_rules = 1;
rule.push_back({type, token_pair.first});
pos = parse_space(token_end, is_nested);
} else if (is_word_char(*pos)) { // rule reference
@ -568,12 +587,15 @@ const char * llama_grammar_parser::parse_sequence(
uint32_t ref_rule_id = get_symbol_id(pos, name_end - pos);
pos = parse_space(name_end, is_nested);
last_sym_start = rule.size();
n_prev_rules = 1;
rule.push_back({LLAMA_GRETYPE_RULE_REF, ref_rule_id});
} else if (*pos == '(') { // grouping
// parse nested alternates into synthesized rule
pos = parse_space(pos + 1, true);
uint32_t n_rules_before = symbol_ids.size();
uint32_t sub_rule_id = generate_symbol_id(rule_name);
pos = parse_alternates(pos, rule_name, sub_rule_id, true);
n_prev_rules = std::max(1u, (uint32_t)symbol_ids.size() - n_rules_before);
last_sym_start = rule.size();
// output reference to synthesized rule
rule.push_back({LLAMA_GRETYPE_RULE_REF, sub_rule_id});
@ -583,6 +605,7 @@ const char * llama_grammar_parser::parse_sequence(
pos = parse_space(pos + 1, is_nested);
} else if (*pos == '.') { // any char
last_sym_start = rule.size();
n_prev_rules = 1;
rule.push_back({LLAMA_GRETYPE_CHAR_ANY, 0});
pos = parse_space(pos + 1, is_nested);
} else if (*pos == '*') {
@ -830,32 +853,54 @@ static bool llama_grammar_match_token(
static void llama_grammar_advance_stack(
const llama_grammar_rules & rules,
const llama_grammar_stack & stack,
llama_grammar_stacks & new_stacks) {
if (stack.empty()) {
if (std::find(new_stacks.begin(), new_stacks.end(), stack) == new_stacks.end()) {
new_stacks.emplace_back(stack);
llama_grammar_stacks & new_stacks) {
std::vector<llama_grammar_stack> todo;
todo.push_back(stack);
auto stack_cmp = [](const llama_grammar_stack & a, const llama_grammar_stack & b) {
return std::lexicographical_compare(a.begin(), a.end(), b.begin(), b.end(),
[](const llama_grammar_element * pa, const llama_grammar_element * pb) {
return pa < pb; // Compare pointer addresses
}
);
};
std::set<llama_grammar_stack, decltype(stack_cmp)> seen(stack_cmp);
while (!todo.empty()) {
llama_grammar_stack curr_stack = std::move(todo.back());
todo.pop_back();
if (seen.find( curr_stack) != seen.end()) {
continue;
}
return;
}
seen.insert(curr_stack);
const llama_grammar_element * pos = stack.back();
if (curr_stack.empty()) {
if (std::find(new_stacks.begin(), new_stacks.end(), curr_stack) == new_stacks.end()) {
new_stacks.emplace_back(std::move(curr_stack));
}
continue;
}
switch (pos->type) {
const llama_grammar_element * pos = curr_stack.back();
switch (pos->type) {
case LLAMA_GRETYPE_RULE_REF: {
const size_t rule_id = static_cast<size_t>(pos->value);
const llama_grammar_element * subpos = rules[rule_id].data();
do {
// init new stack without the top (pos)
llama_grammar_stack new_stack(stack.begin(), stack.end() - 1);
llama_grammar_stack next_stack(curr_stack.begin(), curr_stack.end() - 1);
if (!llama_grammar_is_end_of_sequence(pos + 1)) {
// if this rule ref is followed by another element, add that to stack
new_stack.push_back(pos + 1);
next_stack.push_back(pos + 1);
}
if (!llama_grammar_is_end_of_sequence(subpos)) {
// if alternate is nonempty, add to stack
new_stack.push_back(subpos);
next_stack.push_back(subpos);
}
llama_grammar_advance_stack(rules, new_stack, new_stacks);
todo.push_back(std::move(next_stack));
while (!llama_grammar_is_end_of_sequence(subpos)) {
// scan to end of alternate def
subpos++;
@ -874,9 +919,9 @@ static void llama_grammar_advance_stack(
case LLAMA_GRETYPE_CHAR_ANY:
case LLAMA_GRETYPE_TOKEN:
case LLAMA_GRETYPE_TOKEN_NOT:
if (std::find(new_stacks.begin(), new_stacks.end(), stack) == new_stacks.end()) {
if (std::find(new_stacks.begin(), new_stacks.end(), curr_stack) == new_stacks.end()) {
// only add the stack if it's not a duplicate of one we already have
new_stacks.emplace_back(stack);
new_stacks.emplace_back(std::move(curr_stack));
}
break;
default:
@ -884,6 +929,7 @@ static void llama_grammar_advance_stack(
// (LLAMA_GRETYPE_CHAR_ALT, LLAMA_GRETYPE_CHAR_RNG_UPPER); stack should never be left on
// those
GGML_ABORT("fatal error");
}
}
}

18
tests/test-grammar-integration.cpp
View File

@ -788,6 +788,24 @@ static void test_quantifiers() {
"0xFF 0x12 0xAB 0x00 0x00 0x00",
}
);
test_grammar(
"segfault",
// Grammar
R"""(
root ::= ( [x]* )*
)""",
// Passing strings
{
"",
"x",
"xx"
},
// Failing strings
{
"y",
"yy"
}
);
}
static void test_failure_missing_root() {

4
tests/test-grammar-parser.cpp
View File

@ -145,6 +145,10 @@ int main()
root ::= "a"{,}"
)""");
verify_failure(R"""(
root ::= (((((([^x]*){0,99}){0,99}){0,99}){0,99}){0,99}){0,99}
)""");
verify_failure(R"""(
root ::= "a"{,10}"
)""");

74
tests/test-llama-grammar.cpp
View File

@ -123,25 +123,27 @@ int main()
std::vector<std::vector<llama_grammar_element>> expected_stacks = {
{
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_CHAR, 40},
},
{
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 48},
},
{
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 48},
},
{
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_CHAR, 97},
},
{
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 48},
},
{
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 48},
},
{
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_CHAR, 61},
@ -149,26 +151,24 @@ int main()
{LLAMA_GRETYPE_CHAR, 40},
},
{
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 48},
},
{
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 48},
},
{
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_CHAR, 97},
},
{
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 48},
},
{
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 48},
},
{
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_CHAR, 40},
}};
auto index = 0;
@ -195,9 +195,9 @@ int main()
}
std::vector<llama_grammar_candidate> next_candidates;
next_candidates.resize(24);
next_candidates.resize(23);
for (size_t i = 0; i < 24; ++i)
for (size_t i = 0; i < 23; ++i)
{
uint32_t *cp = new uint32_t[2]; // dynamically allocate memory for code_point
cp[0] = 37 + i;
@ -210,7 +210,6 @@ int main()
{0, 37},
{1, 38},
{2, 39},
{3, 40},
{4, 41},
{5, 42},
{6, 43},
@ -268,6 +267,7 @@ int main()
{0, 37},
{1, 38},
{2, 39},
{3, 40},
{4, 41},
{5, 42},
{6, 43},
@ -287,13 +287,11 @@ int main()
{20, 57},
{21, 58},
{22, 59},
{23, 60},
},
{
{0, 37},
{1, 38},
{2, 39},
{3, 40},
{4, 41},
{5, 42},
{6, 43},
@ -351,6 +349,7 @@ int main()
{0, 37},
{1, 38},
{2, 39},
{3, 40},
{4, 41},
{5, 42},
{6, 43},
@ -370,7 +369,6 @@ int main()
{20, 57},
{21, 58},
{22, 59},
{23, 60},
},
};