Skip to content

ggml : check tensor name lengths in gguf files #10100

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 31, 2024
Merged

ggml : check tensor name lengths in gguf files #10100

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 36 additions & 9 deletions ggml/src/ggml.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22102,18 +22102,46 @@ static size_t gguf_type_size(enum gguf_type type) {
return GGUF_TYPE_SIZE[type];
}

static void gguf_tensor_info_sanitize(struct gguf_tensor_info * info) {
GGML_ASSERT(info->n_dims <= GGML_MAX_DIMS);
GGML_ASSERT(0 <= info->type && info->type < GGML_TYPE_COUNT);
static bool gguf_tensor_info_sanitize(struct gguf_tensor_info * info) {
if (info->n_dims > GGML_MAX_DIMS) {
fprintf(stderr, "%s: invalid number of dimensions (%" PRIu32 ")\n", __func__, info->n_dims);
return false;
}

if (info->type < 0 || info->type >= GGML_TYPE_COUNT) {
fprintf(stderr, "%s: invalid type (%d)\n", __func__, info->type);
return false;
}

if (strlen(info->name.data) >= GGML_MAX_NAME) {
fprintf(stderr, "%s: tensor '%s' name is too long\n", __func__, info->name.data);
return false;
}

for (uint32_t i = 0; i < info->n_dims; ++i) {
GGML_ASSERT(info->ne[i] > 0);
if (info->ne[i] <= 0) {
fprintf(stderr, "%s: invalid number of elements (%" PRIu64 ")\n", __func__, info->ne[i]);
return false;
}
}

// prevent overflow for total number of elements
GGML_ASSERT(INT64_MAX/info->ne[1] > info->ne[0]);
GGML_ASSERT(INT64_MAX/info->ne[2] > info->ne[0]*info->ne[1]);
GGML_ASSERT(INT64_MAX/info->ne[3] > info->ne[0]*info->ne[1]*info->ne[2]);
if (INT64_MAX/info->ne[1] <= info->ne[0]) {
fprintf(stderr, "%s: invalid number of elements (%" PRIu64 ")\n", __func__, info->ne[1]);
return false;
}

if (INT64_MAX/info->ne[2] <= info->ne[0]*info->ne[1]) {
fprintf(stderr, "%s: invalid number of elements (%" PRIu64 ")\n", __func__, info->ne[2]);
return false;
}

if (INT64_MAX/info->ne[3] <= info->ne[0]*info->ne[1]*info->ne[2]) {
fprintf(stderr, "%s: invalid number of elements (%" PRIu64 ")\n", __func__, info->ne[3]);
return false;
}

return true;
}

static bool gguf_fread_el(FILE * file, void * dst, size_t size, size_t * offset) {
Expand Down Expand Up @@ -22414,8 +22442,7 @@ struct gguf_context * gguf_init_from_file(const char * fname, struct gguf_init_p
ok = ok && gguf_fread_el (file, &info->type, sizeof(info->type), &offset);
ok = ok && gguf_fread_el (file, &info->offset, sizeof(info->offset), &offset);

// TODO: return an error instead of crashing with GGML_ASSERT
gguf_tensor_info_sanitize(info);
ok = ok && gguf_tensor_info_sanitize(info);

// make sure there is no duplicated tensor names
for (uint64_t j = 0; j < i && ok; ++j) {
Expand Down
7 changes: 5 additions & 2 deletions src/llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4273,8 +4273,11 @@ struct llama_model_loader {

llama_tensor_weight(const llama_file * file, uint16_t idx, const char * name, const struct gguf_context * gguf_ctx, ggml_tensor * tensor) : idx(idx), tensor(tensor) {
const int tensor_idx = gguf_find_tensor(gguf_ctx, name);
offs = gguf_get_data_offset(gguf_ctx) + gguf_get_tensor_offset(gguf_ctx, tensor_idx);
if (tensor_idx < 0) {
throw std::runtime_error(format("tensor '%s' not found in the model", name));
}

offs = gguf_get_data_offset(gguf_ctx) + gguf_get_tensor_offset(gguf_ctx, tensor_idx);
if (offs + ggml_nbytes(tensor) < offs || offs + ggml_nbytes(tensor) > file->size) {
throw std::runtime_error(format("tensor '%s' data is not within the file bounds, model is corrupted or incomplete", name));
}
Expand Down Expand Up @@ -7426,7 +7429,7 @@ static bool llm_load_tensors(
if (flags & llama_model_loader::TENSOR_NOT_REQUIRED) {
return nullptr;
}
throw std::runtime_error(format("missing tensor %s", tn.str().c_str()));
throw std::runtime_error(format("missing tensor '%s'", tn.str().c_str()));
}

// some models use the token embedding tensor as the output, but since these are used in different layers and with different ops
Expand Down
Loading