Skip to content

split-mixtral: grow tensors[] array instead of assert() (fixes heap OOB write) #32

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

Open
gigioneggiando wants to merge 1 commit into
base: main
Choose a base branch
from
Open

split-mixtral: grow tensors[] array instead of assert() (fixes heap OOB write) #32

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
14 changes: 13 additions & 1 deletion gguf-tools.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -255,7 +255,19 @@ void gguf_tools_split_mixtral(int *experts_id, const char *mixtral_filename, con
* in the output model. */
gguf_tensor tensor_info;
while (gguf_get_tensor(mixtral,&tensor_info)) {
assert(num_tensors < max_tensors);
/* Grow the array instead of asserting: the assert() is compiled out
* under -DNDEBUG (the usual release build), which left a heap
* out-of-bounds write into tensors[] for a source model declaring more
* than max_tensors tensors (an attacker-controlled count in the file).
* Growing also lets a legitimate model with more tensors work. */
if (num_tensors == max_tensors) {
max_tensors *= 2;
tensors = realloc(tensors, sizeof(struct tensor_to_copy)*max_tensors);
if (tensors == NULL) {
perror("Reallocating tensors info array");
exit(1);
}
}

char tn[1024]; // Tensor name as null terminated string.
snprintf(tn,sizeof(tn),"%.*s",(int)tensor_info.namelen, tensor_info.name);
Expand Down