Function weight_buft_supported

subprojects/llama.cpp/src/llama-model.cpp:173–307

checks if the weight tensor can be used with the specified buffer type and device

// checks if the weight tensor can be used with the specified buffer type and device
static bool weight_buft_supported(const llama_hparams & hparams, ggml_tensor * w, ggml_op op, ggml_backend_buffer_type_t buft, ggml_backend_dev_t dev) {
    GGML_ASSERT(w != nullptr);

    if (op == GGML_OP_NONE) {
        return true;
    }

    ggml_init_params params = {
        /*.mem_size   =*/ ggml_tensor_overhead()*8,
        /*.mem_buffer =*/ NULL,
        /*.no_alloc   =*/ true,
    };
    ggml_context_ptr ctx_ptr { ggml_init(params) };
    if (!ctx_ptr) {
        throw std::runtime_error(format("failed to create ggml context"));
    }
    ggml_context * ctx = ctx_ptr.get();

    ggml_tensor * op_tensor = nullptr;

    switch (op) {
        case GGML_OP_GET_ROWS:
            {
                ggml_tensor * b = ggml_new_tensor_1d(ctx, GGML_TYPE_I32, 512);
                op_tensor = ggml_get_rows(ctx, w, b);
            } break;
        case GGML_OP_MUL_MAT:
            {
                ggml_tensor * b = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], 512, w->ne[2], w->ne[3]);
                op_tensor = ggml_mul_mat(ctx, w, b);
            } break;
        case GGML_OP_MUL_MAT_ID:
            {
                int n_expert_used = hparams.n_expert_used;
                ggml_tensor * b = ggml_new_tensor_3d(ctx, GGML_TYPE_F32, w->ne[0], n_expert_used, 512);
                ggml_tensor * ids = ggml_new_tensor_2d(ctx, GGML_TYPE_I32, n_expert_used, 512);
                op_tensor = ggml_mul_mat_id(ctx, w, b, ids);
            } break;
        case GGML_OP_ADD:
            {
                ggml_tensor * a = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], w->ne[1], w->ne[2], w->ne[3]);
                op_tensor = ggml_add(ctx, a, w);
            } break;
        case GGML_OP_ADD_ID:
            {
                int n_expert_used = hparams.n_expert_used;
                ggml_tensor * a = ggml_new_tensor_3d(ctx, GGML_TYPE_F32, w->ne[0], n_expert_used, 512);
                ggml_tensor * c = ggml_new_tensor_2d(ctx, GGML_TYPE_I32, n_expert_used, 512);
                op_tensor = ggml_add_id(ctx, a, w, c);
            } break;
        case GGML_OP_MUL:
            {
                ggml_tensor * a = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], w->ne[1], w->ne[2], w->ne[3]);
                op_tensor = ggml_mul(ctx, a, w);
            } break;
        case GGML_OP_DIV:
            {
                ggml_tensor * a = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, w->ne[0]);