diff --git a/ggml-alloc.c b/ggml-alloc.c index 8ac1d3e..60b86c2 100644 --- a/ggml-alloc.c +++ b/ggml-alloc.c @@ -701,8 +701,13 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c struct ggml_tensor * leaf = graph->leafs[i]; struct hash_node * hn = ggml_gallocr_hash_get(galloc, leaf); galloc->leaf_allocs[i].buffer_id = hn->buffer_id; - galloc->leaf_allocs[i].leaf.offset = hn->offset; - galloc->leaf_allocs[i].leaf.size_max = ggml_backend_buft_get_alloc_size(galloc->bufts[hn->buffer_id], leaf); + if (leaf->view_src || leaf->data) { + galloc->leaf_allocs[i].leaf.offset = SIZE_MAX; + galloc->leaf_allocs[i].leaf.size_max = 0; + } else { + galloc->leaf_allocs[i].leaf.offset = hn->offset; + galloc->leaf_allocs[i].leaf.size_max = ggml_backend_buft_get_alloc_size(galloc->bufts[hn->buffer_id], leaf); + } } // reallocate buffers if needed