tools : reject truncated GGUF tensor data in split and export tools (#30497)

* The problem here in the repo is gguf-split can silently produce corrupted tensor output when the input GGUF file is truncated. The fix is to add tensor-data bounds checks and short-read checks in gguf-split.cpp and export-lora.cpp, and a regression test that checks truncated input is rejected and valid tensor data is preserved.#

* Bug : GGUF-split can silently produce corrupted tensor output when the input GGUF file is truncated. Fix : add short-read checks in gguf-split.cpp (in copy_file_to_file in split_strategy) and export-lora.cpp (in read_tensor_data of file_input) so that truncated input is rejected.

tools/export-lora/export-lora.cpp

@@ -104,6 +104,9 @@ struct file_input {
         auto offset = gguf_get_data_offset(ctx_gguf) + gguf_get_tensor_offset(ctx_gguf, i_tensor_in);
         f_in.seekg(offset);
         f_in.read((char* )buf.data(), len);
+        if (!f_in) {
+            throw std::runtime_error("failed to read data for tensor " + name + ", input file may be truncated");
+        }
     }
 
     ~file_input() {

tools/gguf-split/gguf-split.cpp

@@ -362,6 +362,10 @@ struct split_strategy {
         }
         f_in.seekg(in_offset);
         f_in.read((char *)read_buf.data(), len);
+        if (!f_in) {
+            fprintf(stderr, "%s: failed to read %zu bytes at offset %zu, input file may be truncated\n", __func__, len, in_offset);
+            exit(EXIT_FAILURE);
+        }
         f_out.write((const char *)read_buf.data(), len);
     }
 };