Function make_cpu_buft_list

subprojects/llama.cpp/src/llama-model.cpp:327–386

CPU: ACCEL -> GPU host -> CPU extra -> CPU

// CPU: ACCEL -> GPU host -> CPU extra -> CPU
static buft_list_t make_cpu_buft_list(const std::vector<ggml_backend_dev_t> & devices, bool use_extra_bufts, bool no_host) {
    buft_list_t buft_list;

    // add ACCEL buffer types
    for (size_t i = 0; i < ggml_backend_dev_count(); ++i) {
        ggml_backend_dev_t dev = ggml_backend_dev_get(i);
        if (ggml_backend_dev_type(dev) == GGML_BACKEND_DEVICE_TYPE_ACCEL) {
            auto * buft = ggml_backend_dev_buffer_type(dev);
            // skip
            if (buft != ggml_backend_cpu_buffer_type()) {
                buft_list.emplace_back(dev, buft);
            }
        }
    }

    // add a host buffer type
    // storing the tensors in a host buffer is useful when the processing of large batches
    // is offloaded to a GPU device, since it reduces the time spent on data transfers
    // generally, this will be done using the first device in the list
    // a better approach would be to handle this on a weight-by-weight basis using the offload_op
    // function of the device to determine if it would benefit from being stored in a host buffer
    if (!no_host) {
        for (auto * dev : devices) {
            ggml_backend_buffer_type_t buft = ggml_backend_dev_host_buffer_type(dev);
            if (buft) {
                buft_list.emplace_back(dev, buft);
                break;
            }
        }
    }

    // add extra buffer types
    if (use_extra_bufts) {
        auto * cpu_dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);
        if (cpu_dev == nullptr) {
            throw std::runtime_error(format("%s: no CPU backend found", __func__));
        }

        auto * cpu_reg = ggml_backend_dev_backend_reg(cpu_dev);
        auto ggml_backend_dev_get_extra_bufts_fn = (ggml_backend_dev_get_extra_bufts_t)
            ggml_backend_reg_get_proc_address(cpu_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(cpu_dev);
            while (extra_bufts && *extra_bufts) {
                buft_list.emplace_back(cpu_dev, *extra_bufts);
                ++extra_bufts;
            }
        }
    }

    // add the CPU buffer type
    for (size_t i = 0; i < ggml_backend_dev_count(); ++i) {
        ggml_backend_dev_t dev = ggml_backend_dev_get(i);
        if (ggml_backend_dev_type(dev) == GGML_BACKEND_DEVICE_TYPE_CPU) {
            buft_list.emplace_back(dev, ggml_backend_dev_buffer_type(dev));
        }
    }