Skip to content

ggml-alloc: avoid splitting on zero-size view tensors #13

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
bryanwieg merged 1 commit into from
Sep 20, 2026
Merged

ggml-alloc: avoid splitting on zero-size view tensors #13

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
2 changes: 1 addition & 1 deletion ggml/src/ggml-alloc.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1184,7 +1184,7 @@ static ggml_backend_buffer_t ggml_backend_alloc_ctx_tensors_from_buft_impl(
this_size = GGML_PAD(ggml_backend_buft_get_alloc_size(buft, t), alignment);
}

if (cur_buf_size > 0 && (cur_buf_size + this_size) > max_size) {
if (cur_buf_size > 0 && this_size > 0 && (cur_buf_size + this_size) > max_size) {
// allocate tensors in the current buffer
if (!no_alloc && !alloc_tensor_range(ctx, first, t, buft, cur_buf_size, &buffers, &n_buffers)) {
return NULL;
Expand Down
Loading