mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 03:44:35 +00:00
iq2_xs: CUDA and scalar CPU works
This commit is contained in:
Iwan Kawrakow
parent
9f21b82e4b
commit
9b6e38d8c0
381
ggml-cuda.cu
381
ggml-cuda.cu
@ -486,6 +486,15 @@ typedef struct {
|
||||
} block_iq2_xxs;
|
||||
static_assert(sizeof(block_iq2_xxs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t), "wrong iq2_xxs block size/padding");
|
||||
|
||||
#define QR2_XS 8
|
||||
#define QI2_XS (QK_K / (4*QR2_XS))
|
||||
typedef struct {
|
||||
half d;
|
||||
uint16_t qs[QK_K/8];
|
||||
uint8_t scales[QK_K/32];
|
||||
} block_iq2_xs;
|
||||
static_assert(sizeof(block_iq2_xs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t) + QK_K/32, "wrong iq2_xs block size/padding");
|
||||
|
||||
#define WARP_SIZE 32
|
||||
#define MATRIX_ROW_PADDING 512 // last row of quant. matrices is a multiple of this to avoid out-of-bounds memory accesses
|
||||
|
||||
@ -1328,88 +1337,216 @@ static __global__ void dequantize_block_q6_K(const void * __restrict__ vx, dst_t
|
||||
#endif
|
||||
}
|
||||
|
||||
#define IQ2_STORAGE_CLASS static const __device__
|
||||
#include "iq2-data.h"
|
||||
static const __device__ uint64_t iq2xxs_grid[256] = {
|
||||
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
|
||||
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
|
||||
0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
|
||||
0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
|
||||
0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
|
||||
0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
|
||||
0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
|
||||
0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
|
||||
0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
|
||||
0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
|
||||
0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
|
||||
0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
|
||||
0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
|
||||
0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
|
||||
0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
|
||||
0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
|
||||
0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
|
||||
0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
|
||||
0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
|
||||
0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
|
||||
0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
|
||||
0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
|
||||
0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
|
||||
0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
|
||||
0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
|
||||
0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
|
||||
0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
|
||||
0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
|
||||
0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
|
||||
0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
|
||||
0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
|
||||
0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
|
||||
0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
|
||||
0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
|
||||
0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
|
||||
0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
|
||||
0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
|
||||
0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
|
||||
0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
|
||||
0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
|
||||
0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
|
||||
0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
|
||||
0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
|
||||
0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
|
||||
0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
|
||||
0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
|
||||
0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
|
||||
0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
|
||||
0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
|
||||
0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
|
||||
0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
|
||||
0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
|
||||
0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
|
||||
0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
|
||||
0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
|
||||
0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
|
||||
0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
|
||||
0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
|
||||
0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
|
||||
0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
|
||||
0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
|
||||
0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
|
||||
0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
|
||||
0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
|
||||
};
|
||||
|
||||
//static const __device__ uint64_t kgrid_iq2xxs[256] = {
|
||||
// 0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
|
||||
// 0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
|
||||
// 0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
|
||||
// 0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
|
||||
// 0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
|
||||
// 0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
|
||||
// 0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
|
||||
// 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
|
||||
// 0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
|
||||
// 0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
|
||||
// 0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
|
||||
// 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
|
||||
// 0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
|
||||
// 0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
|
||||
// 0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
|
||||
// 0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
|
||||
// 0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
|
||||
// 0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
|
||||
// 0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
|
||||
// 0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
|
||||
// 0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
|
||||
// 0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
|
||||
// 0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
|
||||
// 0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
|
||||
// 0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
|
||||
// 0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
|
||||
// 0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
|
||||
// 0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
|
||||
// 0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
|
||||
// 0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
|
||||
// 0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
|
||||
// 0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
|
||||
// 0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
|
||||
// 0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
|
||||
// 0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
|
||||
// 0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
|
||||
// 0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
|
||||
// 0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
|
||||
// 0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
|
||||
// 0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
|
||||
// 0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
|
||||
// 0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
|
||||
// 0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
|
||||
// 0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
|
||||
// 0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
|
||||
// 0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
|
||||
// 0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
|
||||
// 0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
|
||||
// 0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
|
||||
// 0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
|
||||
// 0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
|
||||
// 0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
|
||||
// 0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
|
||||
// 0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
|
||||
// 0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
|
||||
// 0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
|
||||
// 0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
|
||||
// 0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
|
||||
// 0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
|
||||
// 0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
|
||||
// 0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
|
||||
// 0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
|
||||
// 0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
|
||||
// 0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
|
||||
//};
|
||||
//
|
||||
//static const __device__ uint8_t ksigns_iq2xs[128] = {
|
||||
// 0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15,
|
||||
// 144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159,
|
||||
// 160, 33, 34, 163, 36, 165, 166, 39, 40, 169, 170, 43, 172, 45, 46, 175,
|
||||
// 48, 177, 178, 51, 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63,
|
||||
// 192, 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, 78, 207,
|
||||
// 80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, 219, 92, 221, 222, 95,
|
||||
// 96, 225, 226, 99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
|
||||
// 240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
|
||||
//};
|
||||
//
|
||||
//static const __device__ uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
|
||||
static const __device__ uint64_t iq2xs_grid[512] = {
|
||||
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
|
||||
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
|
||||
0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
|
||||
0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
|
||||
0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
|
||||
0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
|
||||
0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
|
||||
0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
|
||||
0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
|
||||
0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
|
||||
0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
|
||||
0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
|
||||
0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
|
||||
0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
|
||||
0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
|
||||
0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
|
||||
0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
|
||||
0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
|
||||
0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
|
||||
0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
|
||||
0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
|
||||
0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
|
||||
0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
|
||||
0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
|
||||
0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
|
||||
0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
|
||||
0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
|
||||
0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
|
||||
0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
|
||||
0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
|
||||
0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
|
||||
0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
|
||||
0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
|
||||
0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
|
||||
0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
|
||||
0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
|
||||
0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
|
||||
0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
|
||||
0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
|
||||
0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
|
||||
0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
|
||||
0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
|
||||
0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
|
||||
0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
|
||||
0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
|
||||
0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
|
||||
0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
|
||||
0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
|
||||
0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
|
||||
0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
|
||||
0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
|
||||
0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
|
||||
0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
|
||||
0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
|
||||
0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
|
||||
0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
|
||||
0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
|
||||
0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
|
||||
0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
|
||||
0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
|
||||
0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
|
||||
0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
|
||||
0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
|
||||
0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
|
||||
0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
|
||||
0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
|
||||
0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
|
||||
0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
|
||||
0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
|
||||
0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
|
||||
0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
|
||||
0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
|
||||
0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
|
||||
0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
|
||||
0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
|
||||
0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
|
||||
0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
|
||||
0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
|
||||
0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
|
||||
0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
|
||||
0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
|
||||
0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
|
||||
0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
|
||||
0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
|
||||
0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
|
||||
0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
|
||||
0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
|
||||
0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
|
||||
0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
|
||||
0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
|
||||
0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
|
||||
0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
|
||||
0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
|
||||
0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
|
||||
0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
|
||||
0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
|
||||
0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
|
||||
0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
|
||||
0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
|
||||
0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
|
||||
0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
|
||||
0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
|
||||
0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
|
||||
0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
|
||||
0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
|
||||
0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
|
||||
0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
|
||||
0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
|
||||
0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
|
||||
0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
|
||||
0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
|
||||
0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
|
||||
0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
|
||||
0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
|
||||
0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
|
||||
0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
|
||||
0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
|
||||
0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
|
||||
0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
|
||||
0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
|
||||
0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
|
||||
0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
|
||||
0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
|
||||
0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
|
||||
0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
|
||||
0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
|
||||
0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
|
||||
0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
|
||||
};
|
||||
|
||||
static const __device__ uint8_t ksigns_iq2xs[128] = {
|
||||
0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15,
|
||||
144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159,
|
||||
160, 33, 34, 163, 36, 165, 166, 39, 40, 169, 170, 43, 172, 45, 46, 175,
|
||||
48, 177, 178, 51, 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63,
|
||||
192, 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, 78, 207,
|
||||
80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, 219, 92, 221, 222, 95,
|
||||
96, 225, 226, 99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
|
||||
240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
|
||||
};
|
||||
|
||||
static const __device__ uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
|
||||
|
||||
inline bool ggml_cuda_supports_mmq(enum ggml_type type) {
|
||||
switch (type) {
|
||||
@ -1453,6 +1590,28 @@ static __global__ void dequantize_block_iq2_xxs(const void * __restrict__ vx, ds
|
||||
|
||||
}
|
||||
|
||||
template<typename dst_t>
|
||||
static __global__ void dequantize_block_iq2_xs(const void * __restrict__ vx, dst_t * __restrict__ yy) {
|
||||
|
||||
const int i = blockIdx.x;
|
||||
const block_iq2_xs * x = (const block_iq2_xs *) vx;
|
||||
|
||||
const int tid = threadIdx.x;
|
||||
#if QK_K == 256
|
||||
const int il = tid/8; // 0...3
|
||||
const int ib = tid%8; // 0...7
|
||||
dst_t * y = yy + i*QK_K + 32*ib + 8*il;
|
||||
const uint16_t * q2 = x[i].qs + 4*ib;
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xs_grid + (q2[il] & 511));
|
||||
const float d = (float)x[i].d * (0.5f + ((x[i].scales[ib] >> 4*(il/2)) & 0xf)) * 0.25f;
|
||||
const uint8_t signs = ksigns_iq2xs[q2[il] >> 9];
|
||||
for (int j = 0; j < 8; ++j) y[j] = d * grid[j] * (signs & kmask_iq2xs[j] ? -1.f : 1.f);
|
||||
#else
|
||||
assert(false);
|
||||
#endif
|
||||
|
||||
}
|
||||
|
||||
static __global__ void dequantize_mul_mat_vec_q2_k(const void * __restrict__ vx, const float * __restrict__ yy, float * __restrict__ dst, const int ncols, int nrows) {
|
||||
|
||||
static_assert(16%K_QUANTS_PER_ITERATION == 0, "16 must be divisible by K_QUANTS_PER_ITERATION");
|
||||
@ -4035,6 +4194,42 @@ static __device__ __forceinline__ float vec_dot_iq2_xxs_q8_1(
|
||||
#endif
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ float vec_dot_iq2_xs_q8_1(
|
||||
const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & iqs) {
|
||||
#if QK_K == 256
|
||||
const block_iq2_xs * bq2 = (const block_iq2_xs *) vbq;
|
||||
|
||||
const int ib32 = iqs;
|
||||
const uint16_t * q2 = bq2->qs + 4*ib32;
|
||||
const int8_t * q8 = bq8_1[ib32].qs;
|
||||
const uint8_t ls1 = bq2->scales[ib32] & 0xf;
|
||||
const uint8_t ls2 = bq2->scales[ib32] >> 4;
|
||||
int sumi1 = 0;
|
||||
for (int l = 0; l < 2; ++l) {
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xs_grid + (q2[l] & 511));
|
||||
const uint8_t signs = ksigns_iq2xs[q2[l] >> 9];
|
||||
for (int j = 0; j < 8; ++j) {
|
||||
sumi1 += q8[j] * grid[j] * (signs & kmask_iq2xs[j] ? -1 : 1);
|
||||
}
|
||||
q8 += 8;
|
||||
}
|
||||
int sumi2 = 0;
|
||||
for (int l = 2; l < 4; ++l) {
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xs_grid + (q2[l] & 511));
|
||||
const uint8_t signs = ksigns_iq2xs[q2[l] >> 9];
|
||||
for (int j = 0; j < 8; ++j) {
|
||||
sumi2 += q8[j] * grid[j] * (signs & kmask_iq2xs[j] ? -1 : 1);
|
||||
}
|
||||
q8 += 8;
|
||||
}
|
||||
const float d = (float)bq2->d * (float)bq8_1[ib32].ds.x * 0.25f;
|
||||
return d * ((0.5f + ls1) * sumi1 + (0.5f + ls2) * sumi2);
|
||||
#else
|
||||
assert(false);
|
||||
return 0.f;
|
||||
#endif
|
||||
}
|
||||
|
||||
template <int qk, int qr, int qi, bool need_sum, typename block_q_t, int mmq_x, int mmq_y, int nwarps,
|
||||
allocate_tiles_cuda_t allocate_tiles, load_tiles_cuda_t load_tiles, int vdr, vec_dot_q_mul_mat_cuda_t vec_dot>
|
||||
static __device__ __forceinline__ void mul_mat_q(
|
||||
@ -6038,6 +6233,12 @@ static void dequantize_row_iq2_xxs_cuda(const void * vx, dst_t * y, const int k,
|
||||
dequantize_block_iq2_xxs<<<nb, 32, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
template<typename dst_t>
|
||||
static void dequantize_row_iq2_xs_cuda(const void * vx, dst_t * y, const int k, cudaStream_t stream) {
|
||||
const int nb = k / QK_K;
|
||||
dequantize_block_iq2_xs<<<nb, 32, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
template <typename src_t, typename dst_t>
|
||||
static void convert_unary_cuda(const void * __restrict__ vx, dst_t * __restrict__ y, const int k, cudaStream_t stream) {
|
||||
const int num_blocks = (k + CUDA_DEQUANTIZE_BLOCK_SIZE - 1) / CUDA_DEQUANTIZE_BLOCK_SIZE;
|
||||
@ -6068,6 +6269,8 @@ static to_fp16_cuda_t ggml_get_to_fp16_cuda(ggml_type type) {
|
||||
return dequantize_row_q6_K_cuda;
|
||||
case GGML_TYPE_IQ2_XXS:
|
||||
return dequantize_row_iq2_xxs_cuda;
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
return dequantize_row_iq2_xs_cuda;
|
||||
case GGML_TYPE_F32:
|
||||
return convert_unary_cuda<float>;
|
||||
default:
|
||||
@ -6099,6 +6302,8 @@ static to_fp32_cuda_t ggml_get_to_fp32_cuda(ggml_type type) {
|
||||
return dequantize_row_q6_K_cuda;
|
||||
case GGML_TYPE_IQ2_XXS:
|
||||
return dequantize_row_iq2_xxs_cuda;
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
return dequantize_row_iq2_xs_cuda;
|
||||
case GGML_TYPE_F16:
|
||||
return convert_unary_cuda<half>;
|
||||
default:
|
||||
@ -6302,6 +6507,15 @@ static void mul_mat_vec_iq2_xxs_q8_1_cuda(const void * vx, const void * vy, floa
|
||||
<<<block_nums, block_dims, 0, stream>>>(vx, vy, dst, ncols, nrows);
|
||||
}
|
||||
|
||||
static void mul_mat_vec_iq2_xs_q8_1_cuda(const void * vx, const void * vy, float * dst, const int ncols, const int nrows, cudaStream_t stream) {
|
||||
GGML_ASSERT(ncols % QK_K == 0);
|
||||
const int block_num_y = (nrows + GGML_CUDA_MMV_Y - 1) / GGML_CUDA_MMV_Y;
|
||||
const dim3 block_nums(block_num_y, 1, 1);
|
||||
const dim3 block_dims(WARP_SIZE, GGML_CUDA_MMV_Y, 1);
|
||||
mul_mat_vec_q<QK_K, QI2_XS, block_iq2_xs, 1, vec_dot_iq2_xs_q8_1>
|
||||
<<<block_nums, block_dims, 0, stream>>>(vx, vy, dst, ncols, nrows);
|
||||
}
|
||||
|
||||
static void ggml_mul_mat_q4_0_q8_1_cuda(
|
||||
const void * vx, const void * vy, float * dst, const int ncols_x, const int nrows_x,
|
||||
const int ncols_y, const int nrows_y, const int nrows_dst, cudaStream_t stream) {
|
||||
@ -7874,6 +8088,7 @@ static int64_t get_row_rounding(ggml_type type) {
|
||||
case GGML_TYPE_Q5_K:
|
||||
case GGML_TYPE_Q6_K:
|
||||
case GGML_TYPE_IQ2_XXS:
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
return max_compute_capability >= CC_RDNA2 ? 128 : 64;
|
||||
default:
|
||||
GGML_ASSERT(false);
|
||||
@ -7895,6 +8110,7 @@ static int64_t get_row_rounding(ggml_type type) {
|
||||
case GGML_TYPE_Q4_K:
|
||||
case GGML_TYPE_Q5_K:
|
||||
case GGML_TYPE_IQ2_XXS:
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
return max_compute_capability >= CC_VOLTA ? 128 : 64;
|
||||
case GGML_TYPE_Q6_K:
|
||||
return 64;
|
||||
@ -7948,6 +8164,9 @@ static void ggml_cuda_op_mul_mat_vec_q(
|
||||
case GGML_TYPE_IQ2_XXS:
|
||||
mul_mat_vec_iq2_xxs_q8_1_cuda(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stream);
|
||||
break;
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
mul_mat_vec_iq2_xs_q8_1_cuda(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stream);
|
||||
break;
|
||||
default:
|
||||
GGML_ASSERT(false);
|
||||
break;
|
||||
|
||||
139
ggml-metal.metal
139
ggml-metal.metal
@ -3476,7 +3476,7 @@ kernel void kernel_mul_mv_q6_K_f32(
|
||||
|
||||
// ======================= "True" 2-bit
|
||||
|
||||
constexpr constant static uint64_t kgrid_iq2xxs[256] = {
|
||||
constexpr constant static uint64_t iq2xxs_grid[256] = {
|
||||
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
|
||||
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
|
||||
0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
|
||||
@ -3543,6 +3543,137 @@ constexpr constant static uint64_t kgrid_iq2xxs[256] = {
|
||||
0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
|
||||
};
|
||||
|
||||
constexpr constant static uint64_t iq2xs_grid[512] = {
|
||||
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
|
||||
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
|
||||
0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
|
||||
0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
|
||||
0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
|
||||
0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
|
||||
0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
|
||||
0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
|
||||
0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
|
||||
0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
|
||||
0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
|
||||
0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
|
||||
0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
|
||||
0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
|
||||
0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
|
||||
0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
|
||||
0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
|
||||
0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
|
||||
0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
|
||||
0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
|
||||
0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
|
||||
0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
|
||||
0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
|
||||
0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
|
||||
0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
|
||||
0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
|
||||
0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
|
||||
0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
|
||||
0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
|
||||
0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
|
||||
0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
|
||||
0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
|
||||
0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
|
||||
0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
|
||||
0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
|
||||
0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
|
||||
0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
|
||||
0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
|
||||
0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
|
||||
0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
|
||||
0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
|
||||
0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
|
||||
0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
|
||||
0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
|
||||
0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
|
||||
0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
|
||||
0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
|
||||
0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
|
||||
0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
|
||||
0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
|
||||
0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
|
||||
0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
|
||||
0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
|
||||
0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
|
||||
0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
|
||||
0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
|
||||
0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
|
||||
0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
|
||||
0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
|
||||
0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
|
||||
0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
|
||||
0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
|
||||
0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
|
||||
0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
|
||||
0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
|
||||
0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
|
||||
0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
|
||||
0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
|
||||
0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
|
||||
0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
|
||||
0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
|
||||
0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
|
||||
0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
|
||||
0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
|
||||
0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
|
||||
0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
|
||||
0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
|
||||
0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
|
||||
0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
|
||||
0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
|
||||
0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
|
||||
0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
|
||||
0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
|
||||
0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
|
||||
0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
|
||||
0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
|
||||
0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
|
||||
0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
|
||||
0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
|
||||
0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
|
||||
0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
|
||||
0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
|
||||
0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
|
||||
0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
|
||||
0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
|
||||
0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
|
||||
0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
|
||||
0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
|
||||
0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
|
||||
0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
|
||||
0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
|
||||
0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
|
||||
0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
|
||||
0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
|
||||
0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
|
||||
0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
|
||||
0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
|
||||
0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
|
||||
0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
|
||||
0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
|
||||
0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
|
||||
0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
|
||||
0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
|
||||
0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
|
||||
0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
|
||||
0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
|
||||
0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
|
||||
0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
|
||||
0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
|
||||
0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
|
||||
0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
|
||||
0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
|
||||
0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
|
||||
0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
|
||||
0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
|
||||
0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
|
||||
0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
|
||||
0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
|
||||
};
|
||||
|
||||
constexpr constant static uint8_t ksigns_iq2xs[128] = {
|
||||
0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15,
|
||||
144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159,
|
||||
@ -3600,7 +3731,7 @@ void kernel_mul_mv_iq2_xxs_f32_impl(
|
||||
{
|
||||
int nval = 4;
|
||||
int pos = (32*sgitg + tiisg)*nval;
|
||||
for (int i = 0; i < nval; ++i) values[pos + i] = kgrid_iq2xxs[pos + i];
|
||||
for (int i = 0; i < nval; ++i) values[pos + i] = iq2xxs_grid[pos + i];
|
||||
nval = 2;
|
||||
pos = (32*sgitg + tiisg)*nval;
|
||||
for (int i = 0; i < nval; ++i) shared_signs[pos+i] = ksigns_iq2xs[pos+i];
|
||||
@ -3973,12 +4104,12 @@ void dequantize_iq2_xxs(device const block_iq2_xxs * xb, short il, thread type4x
|
||||
const uint32_t aux32_s = q2[2] | (q2[3] << 16);
|
||||
thread const uint8_t * aux8 = (thread const uint8_t *)&aux32_g;
|
||||
const float dl = d * (0.5f + (aux32_s >> 28)) * 0.25f;
|
||||
constant uint8_t * grid = (constant uint8_t *)(kgrid_iq2xxs + aux8[2*il+0]);
|
||||
constant uint8_t * grid = (constant uint8_t *)(iq2xxs_grid + aux8[2*il+0]);
|
||||
uint8_t signs = ksigns_iq2xs[(aux32_s >> 14*il) & 127];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
grid = (constant uint8_t *)(kgrid_iq2xxs + aux8[2*il+1]);
|
||||
grid = (constant uint8_t *)(iq2xxs_grid + aux8[2*il+1]);
|
||||
signs = ksigns_iq2xs[(aux32_s >> (14*il+7)) & 127];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[2+i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
|
||||
251
ggml-quants.c
251
ggml-quants.c
@ -2342,8 +2342,216 @@ size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t *
|
||||
|
||||
// ====================== "True" 2-bit (de)-quantization
|
||||
|
||||
//#define IQ2_STORAGE_CLASS satic const
|
||||
#include "iq2-data.h"
|
||||
static const uint64_t iq2xxs_grid[256] = {
|
||||
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
|
||||
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
|
||||
0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
|
||||
0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
|
||||
0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
|
||||
0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
|
||||
0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
|
||||
0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
|
||||
0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
|
||||
0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
|
||||
0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
|
||||
0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
|
||||
0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
|
||||
0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
|
||||
0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
|
||||
0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
|
||||
0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
|
||||
0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
|
||||
0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
|
||||
0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
|
||||
0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
|
||||
0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
|
||||
0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
|
||||
0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
|
||||
0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
|
||||
0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
|
||||
0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
|
||||
0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
|
||||
0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
|
||||
0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
|
||||
0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
|
||||
0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
|
||||
0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
|
||||
0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
|
||||
0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
|
||||
0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
|
||||
0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
|
||||
0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
|
||||
0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
|
||||
0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
|
||||
0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
|
||||
0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
|
||||
0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
|
||||
0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
|
||||
0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
|
||||
0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
|
||||
0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
|
||||
0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
|
||||
0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
|
||||
0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
|
||||
0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
|
||||
0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
|
||||
0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
|
||||
0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
|
||||
0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
|
||||
0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
|
||||
0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
|
||||
0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
|
||||
0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
|
||||
0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
|
||||
0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
|
||||
0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
|
||||
0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
|
||||
0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
|
||||
};
|
||||
|
||||
static const uint64_t iq2xs_grid[512] = {
|
||||
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
|
||||
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
|
||||
0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
|
||||
0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
|
||||
0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
|
||||
0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
|
||||
0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
|
||||
0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
|
||||
0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
|
||||
0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
|
||||
0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
|
||||
0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
|
||||
0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
|
||||
0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
|
||||
0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
|
||||
0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
|
||||
0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
|
||||
0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
|
||||
0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
|
||||
0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
|
||||
0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
|
||||
0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
|
||||
0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
|
||||
0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
|
||||
0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
|
||||
0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
|
||||
0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
|
||||
0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
|
||||
0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
|
||||
0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
|
||||
0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
|
||||
0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
|
||||
0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
|
||||
0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
|
||||
0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
|
||||
0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
|
||||
0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
|
||||
0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
|
||||
0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
|
||||
0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
|
||||
0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
|
||||
0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
|
||||
0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
|
||||
0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
|
||||
0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
|
||||
0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
|
||||
0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
|
||||
0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
|
||||
0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
|
||||
0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
|
||||
0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
|
||||
0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
|
||||
0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
|
||||
0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
|
||||
0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
|
||||
0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
|
||||
0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
|
||||
0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
|
||||
0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
|
||||
0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
|
||||
0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
|
||||
0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
|
||||
0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
|
||||
0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
|
||||
0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
|
||||
0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
|
||||
0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
|
||||
0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
|
||||
0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
|
||||
0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
|
||||
0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
|
||||
0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
|
||||
0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
|
||||
0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
|
||||
0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
|
||||
0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
|
||||
0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
|
||||
0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
|
||||
0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
|
||||
0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
|
||||
0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
|
||||
0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
|
||||
0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
|
||||
0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
|
||||
0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
|
||||
0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
|
||||
0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
|
||||
0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
|
||||
0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
|
||||
0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
|
||||
0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
|
||||
0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
|
||||
0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
|
||||
0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
|
||||
0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
|
||||
0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
|
||||
0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
|
||||
0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
|
||||
0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
|
||||
0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
|
||||
0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
|
||||
0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
|
||||
0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
|
||||
0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
|
||||
0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
|
||||
0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
|
||||
0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
|
||||
0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
|
||||
0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
|
||||
0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
|
||||
0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
|
||||
0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
|
||||
0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
|
||||
0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
|
||||
0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
|
||||
0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
|
||||
0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
|
||||
0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
|
||||
0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
|
||||
0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
|
||||
0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
|
||||
0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
|
||||
0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
|
||||
0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
|
||||
0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
|
||||
0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
|
||||
0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
|
||||
0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
|
||||
};
|
||||
|
||||
static const uint8_t ksigns_iq2xs[128] = {
|
||||
0, 129, 130, 3, 132, 5, 6, 135, 136, 9, 10, 139, 12, 141, 142, 15,
|
||||
144, 17, 18, 147, 20, 149, 150, 23, 24, 153, 154, 27, 156, 29, 30, 159,
|
||||
160, 33, 34, 163, 36, 165, 166, 39, 40, 169, 170, 43, 172, 45, 46, 175,
|
||||
48, 177, 178, 51, 180, 53, 54, 183, 184, 57, 58, 187, 60, 189, 190, 63,
|
||||
192, 65, 66, 195, 68, 197, 198, 71, 72, 201, 202, 75, 204, 77, 78, 207,
|
||||
80, 209, 210, 83, 212, 85, 86, 215, 216, 89, 90, 219, 92, 221, 222, 95,
|
||||
96, 225, 226, 99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
|
||||
240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
|
||||
};
|
||||
|
||||
static const uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
|
||||
|
||||
void quantize_row_iq2_xxs_reference(const float * restrict x, block_iq2_xxs * restrict y, int k) {
|
||||
(void)x;
|
||||
@ -2416,14 +2624,14 @@ void dequantize_row_iq2_xs(const block_iq2_xs * restrict x, float * restrict y,
|
||||
|
||||
const float d = GGML_FP16_TO_FP32(x[i].d);
|
||||
|
||||
for (int ib32 = 0; ib32 < QK_K/32; ib32 += 2) {
|
||||
db[0] = d * (0.5f + (x[i].scales[ib32/2] & 0xf)) * 0.25f;
|
||||
db[1] = d * (0.5f + (x[i].scales[ib32/2] >> 4)) * 0.25f;
|
||||
for (int l = 0; l < 8; ++l) {
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xxs_grid + (x[i].qs[4*ib32 + l] & 511));
|
||||
for (int ib32 = 0; ib32 < QK_K/32; ++ib32) {
|
||||
db[0] = d * (0.5f + (x[i].scales[ib32] & 0xf)) * 0.25f;
|
||||
db[1] = d * (0.5f + (x[i].scales[ib32] >> 4)) * 0.25f;
|
||||
for (int l = 0; l < 4; ++l) {
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xs_grid + (x[i].qs[4*ib32 + l] & 511));
|
||||
const uint8_t signs = ksigns_iq2xs[x[i].qs[4*ib32 + l] >> 9];
|
||||
for (int j = 0; j < 8; ++j) {
|
||||
y[j] = db[l/4] * grid[j] * (signs & kmask_iq2xs[j] ? -1.f : 1.f);
|
||||
y[j] = db[l/2] * grid[j] * (signs & kmask_iq2xs[j] ? -1.f : 1.f);
|
||||
}
|
||||
y += 8;
|
||||
}
|
||||
@ -7434,30 +7642,29 @@ void ggml_vec_dot_iq2_xs_q8_K(const int n, float * restrict s, const void * rest
|
||||
const uint8_t * restrict sc = x[i].scales;
|
||||
const int8_t * restrict q8 = y[i].qs;
|
||||
int32_t bsum = 0;
|
||||
for (int ib32 = 0; ib32 < QK_K/32; ib32 += 2) {
|
||||
const uint32_t ls1 = 2*(sc[ib32/2] & 0xf) + 1;
|
||||
const uint32_t ls2 = 2*(sc[ib32/2] >> 4) + 1;
|
||||
int32_t sumi1 = 0;
|
||||
for (int l = 0; l < 4; ++l) {
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xxs_grid + (q2[l] & 511));
|
||||
for (int ib32 = 0; ib32 < QK_K/32; ++ib32) {
|
||||
const uint16_t ls1 = 2*(sc[ib32] & 0xf) + 1;
|
||||
const uint16_t ls2 = 2*(sc[ib32] >> 4) + 1;
|
||||
int32_t sumi = 0;
|
||||
for (int l = 0; l < 2; ++l) {
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xs_grid + (q2[l] & 511));
|
||||
const uint8_t signs = ksigns_iq2xs[q2[l] >> 9];
|
||||
for (int j = 0; j < 8; ++j) {
|
||||
sumi1 += grid[j] * q8[j] * (signs & kmask_iq2xs[j] ? -1 : 1);
|
||||
sumi += grid[j] * q8[j] * (signs & kmask_iq2xs[j] ? -1 : 1);
|
||||
}
|
||||
q8 += 8;
|
||||
}
|
||||
bsum += sumi1 * ls1;
|
||||
q2 += 4;
|
||||
int32_t sumi2 = 0;
|
||||
for (int l = 0; l < 4; ++l) {
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xxs_grid + (q2[l] & 511));
|
||||
bsum += sumi * ls1;
|
||||
sumi = 0;
|
||||
for (int l = 2; l < 4; ++l) {
|
||||
const uint8_t * grid = (const uint8_t *)(iq2xs_grid + (q2[l] & 511));
|
||||
const uint8_t signs = ksigns_iq2xs[q2[l] >> 9];
|
||||
for (int j = 0; j < 8; ++j) {
|
||||
sumi2 += grid[j] * q8[j] * (signs & kmask_iq2xs[j] ? -1 : 1);
|
||||
sumi += grid[j] * q8[j] * (signs & kmask_iq2xs[j] ? -1 : 1);
|
||||
}
|
||||
q8 += 8;
|
||||
}
|
||||
bsum += sumi2 * ls2;
|
||||
bsum += sumi * ls2;
|
||||
q2 += 4;
|
||||
}
|
||||
sumf += d * bsum;
|
||||
|
||||
4
ggml.c
4
ggml.c
@ -19055,8 +19055,8 @@ struct gguf_context * gguf_init_from_file(const char * fname, struct gguf_init_p
|
||||
(int64_t) info->ne[3];
|
||||
|
||||
if (ne % ggml_blck_size(info->type) != 0) {
|
||||
fprintf(stderr, "%s: tensor '%s' number of elements (%" PRId64 ") is not a multiple of block size (%d)\n",
|
||||
__func__, info->name.data, ne, ggml_blck_size(info->type));
|
||||
fprintf(stderr, "%s: tensor '%s' of type %d (%s) number of elements (%" PRId64 ") is not a multiple of block size (%d)\n",
|
||||
__func__, info->name.data, (int)info->type, ggml_type_name(info->type), ne, ggml_blck_size(info->type));
|
||||
fclose(file);
|
||||
gguf_free(ctx);
|
||||
return NULL;
|
||||
|
||||
@ -134,8 +134,9 @@ int main(int argc, char * argv[]) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if ((ggml_type)i == GGML_TYPE_IQ2_XXS) {
|
||||
printf("Skip %s due to missing quantization functionality\n", ggml_type_name((ggml_type) i));
|
||||
const ggml_type ei = (ggml_type)i;
|
||||
if (ei == GGML_TYPE_IQ2_XXS || ei == GGML_TYPE_IQ2_XS) {
|
||||
printf("Skip %s due to missing quantization functionality\n", ggml_type_name(ei));
|
||||
continue;
|
||||
}
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user