vocab : INT32_MIN from llama_tokenize on overflow

Author: retr0reg

common/common.cpp

@@ -1284,6 +1284,9 @@ std::vector<llama_token> common_tokenize(
     int n_tokens = text.length() + 2 * add_special;
     std::vector<llama_token> result(n_tokens);
     n_tokens = llama_tokenize(vocab, text.data(), text.length(), result.data(), result.size(), add_special, parse_special);
+    if (n_tokens == std::numeric_limits<int32_t>::min()) {
+        throw std::runtime_error("Tokenization failed: input text too large, tokenization result exceeds int32_t limit");
+    }
     if (n_tokens < 0) {
         result.resize(-n_tokens);
         int check = llama_tokenize(vocab, text.data(), text.length(), result.data(), result.size(), add_special, parse_special);

include/llama.h

@@ -1087,6 +1087,7 @@ extern "C" {
     /// @param tokens The tokens pointer must be large enough to hold the resulting tokens.
     /// @return Returns the number of tokens on success, no more than n_tokens_max
     /// @return Returns a negative number on failure - the number of tokens that would have been returned
+    /// @return Returns INT32_MIN on overflow (e.g., tokenization result size exceeds int32_t limit)
     /// @param add_special Allow to add BOS and EOS tokens if model is configured to do so.
     /// @param parse_special Allow tokenizing special and/or control tokens which otherwise are not exposed and treated
     ///                      as plaintext. Does not insert a leading space.

src/llama-vocab.cpp

@@ -3062,7 +3062,7 @@ int32_t llama_vocab::tokenize(
     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 -1;
+        return std::numeric_limits<int32_t>::min();
     }
 
     if (n_tokens_max < (int) res.size()) {