Function select_weight_buft

smallthinker/src/llama-model.cpp:297–308

find the first buffer type in the list that can use the tensor

// find the first buffer type in the list that can use the tensor
static ggml_backend_buffer_type_t select_weight_buft(const llama_hparams & hparams, ggml_tensor * tensor, ggml_op op, const buft_list_t & buft_list) {
    GGML_ASSERT(!buft_list.empty());
    for (const auto & cur : buft_list) {
        ggml_backend_dev_t cur_dev = cur.first;
        ggml_backend_buffer_type_t cur_buft = cur.second;
        if (weight_buft_supported(hparams, tensor, op, cur_buft, cur_dev)) {
            return cur_buft;
        }
    }

    return nullptr;
}

// CPU: ACCEL -> GPU host -> CPU extra -> CPU
static buft_list_t make_cpu_buft_list(const std::vector<ggml_backend_dev_t> & devices) {