ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-21 07:58:17 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

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

Browse Source 
* 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>
This commit is contained in:
Aaron Teo
2025-06-01 22:53:57 +08:00
committed by Georgi Gerganov
parent b933d17c30
commit 20f913d119
1 changed files with 14 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
ggml/src/gguf.cpp
View File

@ -347,6 +347,20 @@ struct gguf_context * gguf_init_from_file_impl(FILE * file, struct gguf_init_par
int64_t n_tensors = 0; int64_t n_tensors = 0;
if (ok && gr.read(ctx->version)) { 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) { if (ctx->version == 1) {
GGML_LOG_ERROR("%s: GGUFv1 is no longer supported, please use a more up-to-date version\n", __func__); GGML_LOG_ERROR("%s: GGUFv1 is no longer supported, please use a more up-to-date version\n", __func__);
ok = false; ok = false;