llama-cpp-sys-4 0.10.0

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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145

#pragma OPENCL EXTENSION cl_khr_fp16 : enable

#ifdef cl_intel_required_subgroup_size
#pragma OPENCL EXTENSION cl_intel_required_subgroup_size : enable
#define INTEL_GPU 1
#define REQD_SUBGROUP_SIZE_16 __attribute__((intel_reqd_sub_group_size(16)))
#define REQD_SUBGROUP_SIZE_32 __attribute__((intel_reqd_sub_group_size(32)))
#elif defined(cl_qcom_reqd_sub_group_size)
#pragma OPENCL EXTENSION cl_qcom_reqd_sub_group_size : enable
#define ADRENO_GPU 1
#define REQD_SUBGROUP_SIZE_64  __attribute__((qcom_reqd_sub_group_size("half")))
#define REQD_SUBGROUP_SIZE_128 __attribute__((qcom_reqd_sub_group_size("full")))
#endif

#define QK_K 256

// d, then 64 grid index bytes, then 8 uint32 of packed scale+signs
typedef struct {
    half  d;
    uchar qs[3*QK_K/8];
} block_iq3_xxs;

#undef N_DST
#undef N_SIMDGROUP
#undef N_SIMDWIDTH

#ifdef INTEL_GPU
#define N_DST 4
#define N_SIMDGROUP 1
#define N_SIMDWIDTH 16
#elif defined (ADRENO_GPU)
#define N_DST 4
#define N_SIMDGROUP 1
#define N_SIMDWIDTH 64
#endif

#undef  BLOCK_STRIDE
// 8 threads cover one super block, one 32 element sub block each
#define BLOCK_STRIDE (N_SIMDWIDTH/8)

#ifdef INTEL_GPU
REQD_SUBGROUP_SIZE_16
#elif defined (ADRENO_GPU)
REQD_SUBGROUP_SIZE_64
#endif
kernel void kernel_mul_mv_iq3_xxs_f32(
        global char * src0,
        ulong offset0,
        global char * src1,
        ulong offset1,
        global char * dst,
        ulong offsetd,
        int ne00,
        int ne01,
        ulong nb01,
        ulong nb02,
        ulong nb03,
        int ne12,
        ulong nb11,
        ulong nb12,
        ulong nb13,
        int ne0,
        int ne1,
        int r2,
        int r3
) {
    src0 = src0 + offset0;
    src1 = src1 + offset1;
    dst  = dst  + offsetd;

    int ix = get_sub_group_local_id()/8;  // super block index
    int it = get_sub_group_local_id()%8;  // sub block inside the super block

    int nb = ne00/QK_K;

    int r0 = get_group_id(0);
    int r1 = get_group_id(1);
    int im = get_group_id(2);
    int first_row = (r0 * N_SIMDGROUP + get_sub_group_id()) * N_DST;

    int i12 = im%ne12;
    int i13 = im/ne12;

    ulong offset_src0 = first_row*nb01 + (i12/r2)*nb02 + (i13/r3)*nb03;
    ulong offset_src1 =        r1*nb11 + (i12   )*nb12 + (i13   )*nb13;

    global block_iq3_xxs * x = (global block_iq3_xxs *) (src0 + offset_src0);
    global float         * y = (global float         *) (src1 + offset_src1);

    float yl[32];
    float sumf[N_DST] = {0.f};
    float all_sum;

    global float * y4 = y + ix * QK_K + 32 * it;

    for (int ib = ix; ib < nb; ib += BLOCK_STRIDE) {
        for (int i = 0; i < 32; ++i) {
            yl[i] = y4[i];
        }

        global char * xrow = (global char *)(x + ib);

        // only ne01 output rows exist; reading past them can pull in an inf scale
        for (int row = 0; row < N_DST && first_row + row < ne01; row++) {
            global block_iq3_xxs * xb = (global block_iq3_xxs *)(xrow + row*nb01);

            global uchar * qs = xb->qs + 8*it;

            // Blocks are 98 bytes, so packed signs are only 2-byte aligned.
            global ushort * sw = (global ushort *)(xb->qs + 64 + 4*it);
            uint aux32 = (uint)sw[0] | ((uint)sw[1] << 16);

            float db = (float)xb->d * (0.5f + (float)(aux32 >> 28)) * 0.5f;

            float acc = 0.f;
            for (int l = 0; l < 4; ++l) {
                uchar signs = iq3_xxs_signs((aux32 >> (7*l)) & 127u);
                uint  g1 = iq3_xxs_grid[qs[2*l+0]];
                uint  g2 = iq3_xxs_grid[qs[2*l+1]];

                for (int j = 0; j < 4; ++j) {
                    float s1 = (signs & (1 << j))       ? -1.f : 1.f;
                    float s2 = (signs & (1 << (j+4)))   ? -1.f : 1.f;
                    acc += yl[8*l+j+0] * (float)((g1 >> (8*j)) & 0xFF) * s1;
                    acc += yl[8*l+j+4] * (float)((g2 >> (8*j)) & 0xFF) * s2;
                }
            }

            sumf[row] += db * acc;
        }

        y4 += BLOCK_STRIDE * QK_K;
    }

    global float * dst_f32 = (global float *) dst + im*ne0*ne1 + r1*ne0;

    for (int row = 0; row < N_DST; ++row) {
        all_sum = sub_group_reduce_add(sumf[row]);
        if (first_row + row < ne01) {
            if (get_sub_group_local_id() == 0) {
                dst_f32[first_row + row] = all_sum;
            }
        }
    }
}