Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-27 21:46:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

llama-grammar: fix numeric truncation for token_id parsing (#29382)

Browse Source
This commit is contained in:
Daniel Kuts
2026-09-24 21:43:26 +03:00
committed by GitHub
parent 07fc586e38
commit 5cf3a35287
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-grammar.cpp
+5 -1
View File
@@ -194,7 +194,11 @@ static std::pair<uint32_t, const char *> parse_token(const llama_vocab * vocab,
if (*pos == '[') {
pos++;
const char * int_end = parse_int(pos);
uint32_t token_id = std::stoul(std::string(pos, int_end - pos));
unsigned long id = std::stoul(std::string(pos, int_end - pos));
if (id > std::numeric_limits<uint32_t>::max()) {
throw std::runtime_error(std::string("parsed token id is too big at ") + pos);
}
uint32_t token_id = static_cast<uint32_t>(id);
pos = int_end;
if (*pos != ']') {
throw std::runtime_error(std::string("expecting ']' at ") + pos);