public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

gguf : harden loader against malformed tensor dims and metadata types (llama/25596) 

* gguf : harden loader against malformed tensor dims and metadata types

* gguf: address review on malformed-metadata hardening

- report the expected vs. actual type when general.alignment is not u32
- use ggml_nelements() > 0 for the zero-element guard and keep the
  representability checks visually aligned
- add test-gguf cases for a wrong-typed alignment key and a zero-dim
  tensor (both used to crash: assert-abort and SIGFPE respectively)

Ran tests/test-gguf: 164/164 pass. Used an AI assistant to help draft
these edits; reviewed and verified by me.

* cont : less comments

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
HarrisonSec 2026-08-12 05:07:48 -07:00 committed by Georgi Gerganov
parent 92423afd20
commit b0e3297169
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
ggml/src/gguf.cpp
View File

@ -611,6 +611,13 @@ static struct gguf_context * gguf_init_from_reader(const struct gguf_reader & gr
GGML_ASSERT(int64_t(ctx->kv.size()) == n_kv);
const int alignment_idx = gguf_find_key(ctx, GGUF_KEY_GENERAL_ALIGNMENT);
if (alignment_idx != -1 && gguf_get_kv_type(ctx, alignment_idx) != GGUF_TYPE_UINT32) {
GGML_LOG_ERROR("%s: key '%s' must be of type %s but is %s\n",
__func__, GGUF_KEY_GENERAL_ALIGNMENT, gguf_type_name(GGUF_TYPE_UINT32),
gguf_type_name(gguf_get_kv_type(ctx, alignment_idx)));
gguf_free(ctx);
return nullptr;
}
ctx->alignment = alignment_idx == -1 ? GGUF_DEFAULT_ALIGNMENT : gguf_get_val_u32(ctx, alignment_idx);
if (ctx->alignment == 0 || (ctx->alignment & (ctx->alignment - 1)) != 0) {
@ -682,9 +689,11 @@ static struct gguf_context * gguf_init_from_reader(const struct gguf_reader & gr
}
// check that the total number of elements is representable
if (ok && ((INT64_MAX/info.t.ne[1] <= info.t.ne[0]) ||
(INT64_MAX/info.t.ne[2] <= info.t.ne[0]*info.t.ne[1]) ||
(INT64_MAX/info.t.ne[3] <= info.t.ne[0]*info.t.ne[1]*info.t.ne[2]))) {
// (a zero-element tensor is trivially representable; the guard also avoids a division by zero below)
if (ok && ggml_nelements(&info.t) > 0 &&
((INT64_MAX/info.t.ne[1] <= info.t.ne[0]) ||
(INT64_MAX/info.t.ne[2] <= info.t.ne[0]*info.t.ne[1]) ||
(INT64_MAX/info.t.ne[3] <= info.t.ne[0]*info.t.ne[1]*info.t.ne[2]))) {
GGML_LOG_ERROR("%s: total number of elements in tensor '%s' with shape "
"(%" PRIi64 ", %" PRIi64 ", %" PRIi64 ", %" PRIi64 ") is >= %" PRIi64 "\n",