ggml: check if non-native endian model is being loaded (#13943)

* gguf: prevent non-native endian models from being loaded

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* gguf: update error message

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* gguf: make the non-native endian check more verbose

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml: move ggml_assert location

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml: reword the endianness check error message

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

---------

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml/src/gguf.cpp

@@ -347,6 +347,20 @@ struct gguf_context * gguf_init_from_file_impl(FILE * file, struct gguf_init_par
     int64_t n_tensors = 0;
 
     if (ok && gr.read(ctx->version)) {
+        /*
+         * bit layout is different when reading non-native endian models.
+         * assuming that the GGUF version is 3, the non-native endian model
+         * would read it as 0x30000000. we can use the AND operation against
+         * the last 4 hexadecimal digits to check if the model is the same
+         * endianness as the host system.
+        */
+        if ((ctx->version & 0x0000FFFF) == 0x00000000) {
+            GGML_LOG_ERROR("%s: failed to load model: this GGUF file version %" PRIu32 " is extremely large, is there a mismatch between the host and model endianness?\n", __func__, ctx->version);
+            gguf_free(ctx);
+            return nullptr;
+        }
+
+        GGML_ASSERT(ctx->version > 0 && ctx->version <= 65535);
         if (ctx->version == 1) {
             GGML_LOG_ERROR("%s: GGUFv1 is no longer supported, please use a more up-to-date version\n", __func__);
             ok = false;