tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-04 16:23:49 -04:00
Code Issues Packages Projects Releases Wiki Activity

vocab : prevent tokenizer overflow (#14301)

Browse Source 
* vocab : prevent stack overflow in tokenize

* vocab : return error instead of aborting on oversized token count

* vocab : INT32_MIN from llama_tokenize on overflow
This commit is contained in:
Ruikai Peng
2025-06-20 22:13:06 +08:00
committed by GitHub
parent 8308f98c7f
commit dd6e6d0b6a
3 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llama-vocab.cpp
View File

@@ -3074,6 +3074,11 @@ int32_t llama_vocab::tokenize(
bool add_special,
bool parse_special) const {
auto res = tokenize(std::string(text, text_len), add_special, parse_special);
if (res.size() >= static_cast<size_t>(std::numeric_limits<int32_t>::max())) {
LLAMA_LOG_ERROR("%s: tokenization result size %zu exceeds int32_t limit\n", __func__, res.size());
return std::numeric_limits<int32_t>::min();
}
if (n_tokens_max < (int) res.size()) {
// LLAMA_LOG_ERROR("%s: too many tokens\n", __func__);
return -((int) res.size());