22 lines
1.1 KiB
Diff
22 lines
1.1 KiB
Diff
|
--- ggml/src/ggml-backend.cpp 2026-05-10 17:51:34
|
||
|
|
+++ ggml/src/ggml-backend.cpp 2026-05-10 17:55:54
|
||
|
|
@@ -894,6 +894,18 @@
|
||
|
|
|
||
|
|
if (tensor->buffer || (tensor->view_src && tensor->view_src->buffer)) {
|
||
|
|
// since the tensor is pre-allocated, it cannot be moved to another backend
|
||
|
|
+ // Try to find a backend matching this buffer, ignoring op support
|
||
|
|
+ // (some ops like NONE or data movement ops may not be registered on all backends)
|
||
|
|
+ {
|
||
|
|
+ ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer;
|
||
|
|
+ for (int i = 0; i < sched->n_backends; i++) {
|
||
|
|
+ if (ggml_backend_supports_buft(sched->backends[i], buf->buft)) {
|
||
|
|
+ cur_backend_id = i;
|
||
|
|
+ SET_CAUSE(tensor, "1.buft");
|
||
|
|
+ return cur_backend_id;
|
||
|
|
+ }
|
||
|
|
+ }
|
||
|
|
+ }
|
||
|
|
ggml_backend_buffer_t buffer = tensor->view_src ? tensor->view_src->buffer : tensor->buffer;
|
||
|
|
GGML_ABORT("pre-allocated tensor (%s) in a buffer (%s) that cannot run the operation (%s)", tensor->name, ggml_backend_buffer_name(buffer), ggml_op_name(tensor->op));
|
||
|
|
}
|