Function make_gpu_buft_list

subprojects/llama.cpp/src/llama-model.cpp:389–431

GPU: split if LLAMA_SPLIT_MODE_ROW -> GPU

// GPU: split if LLAMA_SPLIT_MODE_ROW -> GPU
static buft_list_t make_gpu_buft_list(ggml_backend_dev_t dev, llama_split_mode split_mode, const float * tensor_split) {
    buft_list_t buft_list;

    // add the device split buffer type if requested and available
    if (split_mode == LLAMA_SPLIT_MODE_ROW) {
        ggml_backend_reg_t reg = ggml_backend_dev_backend_reg(dev);
        auto ggml_backend_split_buffer_type_fn = (ggml_backend_split_buffer_type_t)
            ggml_backend_reg_get_proc_address(reg, "ggml_backend_split_buffer_type");
        if (ggml_backend_split_buffer_type_fn) {
            size_t dev_index = [&]() {
                auto * reg = ggml_backend_dev_backend_reg(dev);
                for (size_t i = 0; i < ggml_backend_reg_dev_count(reg); ++i) {
                    if (ggml_backend_reg_dev_get(reg, i) == dev) {
                        return i;
                    }
                }
                throw std::runtime_error(format("device %s not found in its backend reg", ggml_backend_dev_name(dev)));
            }();
            auto * buft = ggml_backend_split_buffer_type_fn(dev_index, tensor_split);
            if (buft != nullptr) {
                buft_list.emplace_back(dev, buft);
            }
        }
    }

    // add the device default buffer type
    buft_list.emplace_back(dev, ggml_backend_dev_buffer_type(dev));

    // add the device extra buffer type (if any)
    ggml_backend_reg_t reg = ggml_backend_dev_backend_reg(dev);
    auto ggml_backend_dev_get_extra_bufts_fn = (ggml_backend_dev_get_extra_bufts_t)
        ggml_backend_reg_get_proc_address(reg, "ggml_backend_dev_get_extra_bufts");

    if (ggml_backend_dev_get_extra_bufts_fn) {
        ggml_backend_buffer_type_t * extra_bufts = ggml_backend_dev_get_extra_bufts_fn(dev);
        while (extra_bufts && *extra_bufts) {
            buft_list.emplace_back(dev, *extra_bufts);
            ++extra_bufts;
        }
    }

    return buft_list;
}

struct llama_model::impl {
    impl() = default;