[Backend][Common]Some error message explanation

[luoyu-intel]

Hi @slaren @ggerganov , I'm debugging the accuracy error of the SYCL backend. I found some error messages while built with debug and ngl is less than 32(llama2 32 layers).
The error messages are :

...
ggml_backend_sched_alloc_splits: failed to allocate graph, reserving
....

....
ggml_gallocr_needs_realloc: node inp_embd is not valid
ggml_gallocr_alloc_graph: cannot reallocate multi buffer graph automatically, call reserve
ggml_backend_sched_alloc_splits: failed to allocate graph, reserving

code is here:

// allocate graph
    if (backend_ids_changed || !ggml_gallocr_alloc_graph(sched->galloc, sched->graph)) {
        // the re-allocation may cause the split inputs to be moved to a different address
        ggml_backend_sched_synchronize(sched);
#ifndef NDEBUG
        fprintf(stderr, "%s: failed to allocate graph, reserving\n", __func__);
#endif
        ggml_gallocr_reserve_n(sched->galloc, sched->graph, sched->node_backend_ids, sched->leaf_backend_ids);
        if (!ggml_gallocr_alloc_graph(sched->galloc, sched->graph)) {
            fprintf(stderr, "%s: failed to allocate graph\n", __func__);
            return false;
        }
    }

Are these messages I listed error messages? Or can I just ignore them?

[slaren]

Hi, these are trace messages to help understand the behavior of the allocator, and do not indicate an error. You can ignore them.