llama-cpp-sys-2 0.1.157

Low Level Bindings to llama.cpp
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96

#include "../node_context.h"
#include "../op_table.h"
#include "../utils.h"

#include <cassert>
#include <cstdint>
#include <memory>
#include <openvino/core/node.hpp>
#include <openvino/core/node_output.hpp>
#include <openvino/core/type.hpp>
#include <openvino/frontend/exception.hpp>
#include <openvino/op/broadcast.hpp>
#include <openvino/op/concat.hpp>
#include <openvino/op/constant.hpp>
#include <openvino/op/convert.hpp>
#include <openvino/op/gather.hpp>
#include <openvino/op/reshape.hpp>
#include <openvino/op/scatter_elements_update.hpp>
#include <openvino/op/scatter_update.hpp>
#include <openvino/op/shape_of.hpp>
#include <openvino/op/slice.hpp>
#include <openvino/op/squeeze.hpp>
#include <openvino/op/transpose.hpp>
#include <vector>

namespace ov {
namespace frontend {
namespace ggml {
namespace op {

OutputVector translate_set_rows(const NodeContext & context) {
    num_inputs_check(context, 3, 3);

    auto data = process_view_input_new(context, 0);
    auto indices = process_view_input_new(context, 1);
    auto dst = process_view_input_new(context, 2);

    data = std::make_shared<ov::op::v0::Convert>(data, context.get_output_type());

    const auto indices_shape = context.get_input_shape(1);
    const bool multidim_indices = indices_shape.rank().is_static() &&
                                  indices_shape.rank().get_length() == 4 &&
                                  ((indices_shape[1].is_static() && indices_shape[1].get_length() > 1) ||
                                   (indices_shape[2].is_static() && indices_shape[2].get_length() > 1));

    auto axes = ov::op::v0::Constant::create(ov::element::i64, ov::Shape{}, {2});

    Output<Node> res;
    if (context.is_stateful()) {
        int concat_axis = 1;
        int64_t dim2 = dst.get_partial_shape()[2].get_length();
        int64_t dim3 = dst.get_partial_shape()[3].get_length();
        data = std::make_shared<ov::op::v1::Reshape>(
            data, ov::op::v0::Constant::create(ov::element::i64, {4}, {(int64_t) 1, (int64_t) -1, dim2, dim3}), false);
        res = std::make_shared<ov::op::v0::Concat>(OutputVector{dst, data}, concat_axis);
    } else if (multidim_indices) {
        auto updates_shape = std::make_shared<ov::op::v3::ShapeOf>(data, ov::element::i64);

        auto indices_rank3 = std::make_shared<ov::op::v0::Squeeze>(
            indices, ov::op::v0::Constant::create(ov::element::i64, {1}, {0}));
        auto one = ov::op::v0::Constant::create(ov::element::i64, {1}, {1});
        auto indices_rank4_shape = std::make_shared<ov::op::v0::Concat>(OutputVector{get_dimensions(updates_shape, {0, 1, 2}), one}, 0);
        auto indices_rank4 = std::make_shared<ov::op::v1::Reshape>(indices_rank3, indices_rank4_shape, false);
        auto broadcasted_indices = std::make_shared<ov::op::v3::Broadcast>(indices_rank4, updates_shape);

        res = std::make_shared<ov::op::v3::ScatterElementsUpdate>(dst, broadcasted_indices, data, axes);
    } else {
        auto row_size = context.get_input_shape(2)[3].get_length();
        auto ind_squeezed = std::make_shared<ov::op::v0::Squeeze>(
            indices, ov::op::v0::Constant::create(ov::element::i64, {3}, {0, 1, 2}));
        auto data_reshaped = std::make_shared<ov::op::v1::Reshape>(
            data,
            ov::op::v0::Constant::create(ov::element::i64, {4},
                                         {(int64_t) 1, (int64_t) 1, (int64_t) -1, (int64_t) row_size}),
            false);
        res = std::make_shared<ov::op::v3::ScatterUpdate>(dst, ind_squeezed, data_reshaped, axes);
    }

    auto dst_reshape = ov::as_type_ptr<ov::op::v1::Reshape>(dst.get_node_shared_ptr());
    if (!multidim_indices && dst_reshape) {
        // Fix the case of multiple sequences, reshape back to original shape [1, n_seq, ctx_per_seq, emb]
        // ctx_per_seq is not fixed due to llama-bench compatibility
        auto dst_shape_partial = dst_reshape->get_input_partial_shape(0);
        std::vector<int64_t> dst_shape = {dst_shape_partial[0].get_length(), dst_shape_partial[1].get_length(),
                                          dst_shape_partial[2].is_static() ? dst_shape_partial[2].get_length() : -1,
                                          dst_shape_partial[3].get_length()};
        res = std::make_shared<ov::op::v1::Reshape>(res, ov::op::v0::Constant::create(ov::element::i64, {4}, dst_shape),
                                                    false);
    }
    return rename_outputs_with_suffix({res}, context.get_name());
}

}  // namespace op
}  // namespace ggml
}  // namespace frontend
}  // namespace ov