Skip to content

ggml-backend : only offload from host buffers (fix) #11124

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
Jan 7, 2025
Merged

ggml-backend : only offload from host buffers (fix) #11124

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
4 changes: 2 additions & 2 deletions ggml/src/ggml-backend.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -761,10 +761,10 @@ static int ggml_backend_sched_backend_id_from_cur(ggml_backend_sched_t sched, st
}
// skip ROPE since the rope freqs tensor is too small to choose a backend based on it
// not an ideal solution
if (tensor->op != GGML_OP_ROPE && src->buffer != NULL && src->buffer->usage == GGML_BACKEND_BUFFER_USAGE_WEIGHTS && ggml_backend_buffer_is_host(src->buffer)) {
if (tensor->op != GGML_OP_ROPE && src->buffer != NULL && src->buffer->usage == GGML_BACKEND_BUFFER_USAGE_WEIGHTS) {
int src_backend_id = ggml_backend_sched_backend_from_buffer(sched, src, tensor);
// check if a backend with higher prio wants to offload the op
if (src_backend_id == sched->n_backends - 1) {
if (src_backend_id == sched->n_backends - 1 && ggml_backend_buffer_is_host(src->buffer)) {
for (int b = 0; b < src_backend_id; b++) {
if (ggml_backend_supports_op(sched->backends[b], tensor) && ggml_backend_offload_op(sched->backends[b], tensor)) {
SET_CAUSE(tensor, "1.off");
Expand Down
2 changes: 2 additions & 0 deletions ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4169,6 +4169,8 @@ static ggml_backend_buffer_t ggml_backend_cpu_aarch64_buffer_type_alloc_buffer(g
buffer->buft = buft;
buffer->iface.init_tensor = ggml_backend_cpu_aarch64_buffer_init_tensor;
buffer->iface.set_tensor = ggml_backend_cpu_aarch64_buffer_set_tensor;
buffer->iface.get_tensor = nullptr;
buffer->iface.cpy_tensor = nullptr;
return buffer;
}

Expand Down
Loading