mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-11 01:24:36 +00:00
Merge branch 'master' into concedo_experimental
# Conflicts: # Makefile # README.md # flake.lock # ggml-cuda.cu # llama.cpp # tests/test-backend-ops.cpp # tests/test-quantize-fns.cpp
This commit is contained in:
Concedo
commit
ad638285de
26 changed files with 3393 additions and 589 deletions
552
ggml-cuda.cu
552
ggml-cuda.cu
|
|
@ -523,6 +523,17 @@ typedef struct {
|
|||
} 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");
|
||||
|
||||
// 2.5625 bpw quants
|
||||
#define QR2_S 8
|
||||
#define QI2_S (QK_K / (4*QR2_S))
|
||||
typedef struct {
|
||||
half d;
|
||||
uint8_t qs[QK_K/4];
|
||||
uint8_t qh[QK_K/32];
|
||||
uint8_t scales[QK_K/32];
|
||||
} block_iq2_s;
|
||||
static_assert(sizeof(block_iq2_s) == sizeof(ggml_fp16_t) + QK_K/4 + QK_K/16, "wrong iq2_s block size/padding");
|
||||
|
||||
#define QR3_XXS 8
|
||||
#define QI3_XXS (QK_K / (4*QR3_XXS))
|
||||
typedef struct {
|
||||
|
|
@ -560,6 +571,18 @@ typedef struct {
|
|||
} block_iq4_nl;
|
||||
static_assert(sizeof(block_iq4_nl) == sizeof(ggml_fp16_t) + QK4_NL/2, "wrong iq4_nl block size/padding");
|
||||
|
||||
// QR4_XS = 8 is very slightly faster than QR4_XS = 4
|
||||
#define QR4_XS 8
|
||||
#define QI4_XS (QK_K / (4*QR4_XS))
|
||||
typedef struct {
|
||||
half d;
|
||||
uint16_t scales_h;
|
||||
uint8_t scales_l[QK_K/64];
|
||||
uint8_t qs[QK_K/2];
|
||||
} block_iq4_xs;
|
||||
static_assert(sizeof(block_iq4_xs) == sizeof(ggml_fp16_t) + sizeof(uint16_t) + QK_K/64 + QK_K/2, "wrong iq4_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
|
||||
|
||||
|
|
@ -686,18 +709,20 @@ static __device__ __forceinline__ float2 warp_reduce_sum(float2 a) {
|
|||
return a;
|
||||
}
|
||||
|
||||
//static __device__ __forceinline__ half2 warp_reduce_sum(half2 a) {
|
||||
//#if !(defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)) && __CUDA_ARCH__ >= CC_PASCAL
|
||||
//#pragma unroll
|
||||
// for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
// a = __hadd2(a, __shfl_xor_sync(0xffffffff, a, mask, 32));
|
||||
// }
|
||||
// return a;
|
||||
//#else
|
||||
// (void) a;
|
||||
// NO_DEVICE_CODE;
|
||||
//#endif // !(defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)) && __CUDA_ARCH__ >= CC_PASCAL
|
||||
//}
|
||||
#ifdef GGML_CUDA_F16
|
||||
static __device__ __forceinline__ half2 warp_reduce_sum(half2 a) {
|
||||
#if !(defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)) && __CUDA_ARCH__ >= CC_PASCAL
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
a = __hadd2(a, __shfl_xor_sync(0xffffffff, a, mask, 32));
|
||||
}
|
||||
return a;
|
||||
#else
|
||||
(void) a;
|
||||
NO_DEVICE_CODE;
|
||||
#endif // !(defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)) && __CUDA_ARCH__ >= CC_PASCAL
|
||||
}
|
||||
#endif // GGML_CUDA_F16
|
||||
|
||||
static __device__ __forceinline__ float warp_reduce_max(float x) {
|
||||
#pragma unroll
|
||||
|
|
@ -1690,6 +1715,265 @@ static const __device__ uint64_t iq2xs_grid[512] = {
|
|||
0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
|
||||
};
|
||||
|
||||
static const __device__ uint64_t iq2s_grid[1024] = {
|
||||
0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
|
||||
0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
|
||||
0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
|
||||
0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
|
||||
0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
|
||||
0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
|
||||
0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
|
||||
0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
|
||||
0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
|
||||
0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
|
||||
0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
|
||||
0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
|
||||
0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
|
||||
0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
|
||||
0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
|
||||
0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
|
||||
0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
|
||||
0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
|
||||
0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
|
||||
0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
|
||||
0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
|
||||
0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
|
||||
0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
|
||||
0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
|
||||
0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
|
||||
0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
|
||||
0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
|
||||
0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
|
||||
0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
|
||||
0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
|
||||
0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
|
||||
0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
|
||||
0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
|
||||
0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
|
||||
0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
|
||||
0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
|
||||
0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
|
||||
0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
|
||||
0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
|
||||
0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
|
||||
0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
|
||||
0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
|
||||
0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
|
||||
0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
|
||||
0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
|
||||
0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
|
||||
0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
|
||||
0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
|
||||
0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
|
||||
0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
|
||||
0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
|
||||
0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
|
||||
0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
|
||||
0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
|
||||
0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
|
||||
0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
|
||||
0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
|
||||
0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
|
||||
0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
|
||||
0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
|
||||
0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
|
||||
0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
|
||||
0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
|
||||
0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
|
||||
0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
|
||||
0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
|
||||
0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
|
||||
0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
|
||||
0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
|
||||
0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
|
||||
0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
|
||||
0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
|
||||
0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
|
||||
0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
|
||||
0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
|
||||
0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
|
||||
0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
|
||||
0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
|
||||
0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
|
||||
0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
|
||||
0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
|
||||
0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
|
||||
0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
|
||||
0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
|
||||
0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
|
||||
0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
|
||||
0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
|
||||
0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
|
||||
0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
|
||||
0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
|
||||
0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
|
||||
0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
|
||||
0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
|
||||
0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
|
||||
0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
|
||||
0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
|
||||
0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
|
||||
0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
|
||||
0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
|
||||
0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
|
||||
0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
|
||||
0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
|
||||
0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
|
||||
0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
|
||||
0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
|
||||
0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
|
||||
0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
|
||||
0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
|
||||
0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
|
||||
0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
|
||||
0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
|
||||
0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
|
||||
0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
|
||||
0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
|
||||
0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
|
||||
0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
|
||||
0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
|
||||
0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
|
||||
0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
|
||||
0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
|
||||
0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
|
||||
0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
|
||||
0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
|
||||
0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
|
||||
0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
|
||||
0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
|
||||
0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
|
||||
0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
|
||||
0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
|
||||
0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
|
||||
0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
|
||||
0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
|
||||
0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
|
||||
0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
|
||||
0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
|
||||
0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
|
||||
0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
|
||||
0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
|
||||
0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
|
||||
0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
|
||||
0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
|
||||
0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
|
||||
0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
|
||||
0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
|
||||
0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
|
||||
0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
|
||||
0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
|
||||
0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
|
||||
0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
|
||||
0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
|
||||
0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
|
||||
0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
|
||||
0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
|
||||
0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
|
||||
0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
|
||||
0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
|
||||
0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
|
||||
0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
|
||||
0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
|
||||
0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
|
||||
0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
|
||||
0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
|
||||
0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
|
||||
0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
|
||||
0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
|
||||
0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
|
||||
0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
|
||||
0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
|
||||
0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
|
||||
0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
|
||||
0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
|
||||
0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
|
||||
0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
|
||||
0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
|
||||
0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
|
||||
0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
|
||||
0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
|
||||
0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
|
||||
0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
|
||||
0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
|
||||
0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
|
||||
0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
|
||||
0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
|
||||
0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
|
||||
0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
|
||||
0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
|
||||
0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
|
||||
0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
|
||||
0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
|
||||
0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
|
||||
0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
|
||||
0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
|
||||
0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
|
||||
0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
|
||||
0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
|
||||
0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
|
||||
0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
|
||||
0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
|
||||
0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
|
||||
0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
|
||||
0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
|
||||
0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
|
||||
0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
|
||||
0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
|
||||
0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
|
||||
0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
|
||||
0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
|
||||
0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
|
||||
0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
|
||||
0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
|
||||
0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
|
||||
0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
|
||||
0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
|
||||
0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
|
||||
0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
|
||||
0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
|
||||
0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
|
||||
0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
|
||||
0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
|
||||
0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
|
||||
0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
|
||||
0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
|
||||
0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
|
||||
0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
|
||||
0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
|
||||
0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
|
||||
0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
|
||||
0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
|
||||
0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
|
||||
0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
|
||||
0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
|
||||
0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
|
||||
0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
|
||||
0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
|
||||
0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
|
||||
0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
|
||||
0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
|
||||
0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
|
||||
0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
|
||||
0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
|
||||
0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
|
||||
0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
|
||||
0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
|
||||
0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
|
||||
0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
|
||||
0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
|
||||
0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
|
||||
0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
|
||||
0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
|
||||
0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
|
||||
0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
|
||||
0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
|
||||
0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
|
||||
0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
|
||||
0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
|
||||
0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
|
||||
};
|
||||
|
||||
static const __device__ uint32_t iq3xxs_grid[256] = {
|
||||
0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
|
||||
0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
|
||||
|
|
@ -2038,6 +2322,27 @@ static __global__ void dequantize_block_iq2_xs(const void * __restrict__ vx, dst
|
|||
|
||||
}
|
||||
|
||||
template<typename dst_t>
|
||||
static __global__ void dequantize_block_iq2_s(const void * __restrict__ vx, dst_t * __restrict__ yy) {
|
||||
|
||||
const int i = blockIdx.x;
|
||||
const block_iq2_s * x = (const block_iq2_s *) 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 uint8_t * grid = (const uint8_t *)(iq2s_grid + (x[i].qs[4*ib+il] | ((x[i].qh[ib] << (8-2*il)) & 0x300)));
|
||||
const float d = (float)x[i].d * (0.5f + ((x[i].scales[ib] >> 4*(il/2)) & 0xf)) * 0.25f;
|
||||
const uint8_t signs = x[i].qs[QK_K/8+4*ib+il];
|
||||
for (int j = 0; j < 8; ++j) y[j] = d * grid[j] * (signs & kmask_iq2xs[j] ? -1.f : 1.f);
|
||||
#else
|
||||
assert(false);
|
||||
#endif
|
||||
|
||||
}
|
||||
|
||||
template<typename dst_t>
|
||||
static __global__ void dequantize_block_iq3_xxs(const void * __restrict__ vx, dst_t * __restrict__ yy) {
|
||||
|
||||
|
|
@ -2135,6 +2440,25 @@ static __global__ void dequantize_block_iq4_nl(const void * __restrict__ vx, dst
|
|||
|
||||
}
|
||||
|
||||
template<typename dst_t>
|
||||
static __global__ void dequantize_block_iq4_xs(const void * __restrict__ vx, dst_t * __restrict__ yy) {
|
||||
|
||||
const int i = blockIdx.x;
|
||||
const block_iq4_xs * x = (const block_iq4_xs *)vx;
|
||||
|
||||
const int tid = threadIdx.x;
|
||||
const int il = tid/8; // 0...3
|
||||
const int ib = tid%8; // 0...7
|
||||
dst_t * y = yy + i*QK_K + 32*ib + 4*il;
|
||||
const uint8_t * q4 = x[i].qs + 16*ib + 4*il;
|
||||
const float d = (float)x[i].d * ((((x[i].scales_l[ib/2] >> 4*(ib%2)) & 0xf) | (((x[i].scales_h >> 2*ib) & 3) << 4)) - 32);
|
||||
for (int j = 0; j < 4; ++j) {
|
||||
y[j+ 0] = d * kvalues_iq4nl[q4[j] & 0xf];
|
||||
y[j+16] = d * kvalues_iq4nl[q4[j] >> 4];
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
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");
|
||||
|
|
@ -2231,10 +2555,7 @@ static __global__ void dequantize_mul_mat_vec_q2_k(const void * __restrict__ vx,
|
|||
#endif
|
||||
|
||||
// sum up partial sums and write back result
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
tmp = warp_reduce_sum(tmp);
|
||||
|
||||
if (threadIdx.x == 0) {
|
||||
dst[row] = tmp;
|
||||
|
|
@ -2335,10 +2656,7 @@ static __global__ void dequantize_mul_mat_vec_q3_k(const void * __restrict__ vx,
|
|||
#endif
|
||||
|
||||
// sum up partial sums and write back result
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
tmp = warp_reduce_sum(tmp);
|
||||
|
||||
if (threadIdx.x == 0) {
|
||||
dst[row] = tmp;
|
||||
|
|
@ -2471,10 +2789,7 @@ static __global__ void dequantize_mul_mat_vec_q4_k(const void * __restrict__ vx,
|
|||
#endif
|
||||
|
||||
// sum up partial sums and write back result
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
tmp = warp_reduce_sum(tmp);
|
||||
|
||||
if (tid == 0) {
|
||||
dst[row] = tmp;
|
||||
|
|
@ -2587,10 +2902,7 @@ static __global__ void dequantize_mul_mat_vec_q5_k(const void * __restrict__ vx,
|
|||
#endif
|
||||
|
||||
// sum up partial sums and write back result
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
tmp = warp_reduce_sum(tmp);
|
||||
|
||||
if (threadIdx.x == 0) {
|
||||
dst[row] = tmp;
|
||||
|
|
@ -2697,10 +3009,7 @@ static __global__ void dequantize_mul_mat_vec_q6_k(const void * __restrict__ vx,
|
|||
#endif
|
||||
|
||||
// sum up partial sums and write back result
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
tmp = warp_reduce_sum(tmp);
|
||||
|
||||
if (tid == 0) {
|
||||
dst[row] = tmp;
|
||||
|
|
@ -2735,11 +3044,8 @@ static __global__ void quantize_q8_1(const float * __restrict__ x, void * __rest
|
|||
float amax = fabsf(xi);
|
||||
float sum = xi;
|
||||
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
amax = fmaxf(amax, __shfl_xor_sync(0xffffffff, amax, mask, 32));
|
||||
sum += __shfl_xor_sync(0xffffffff, sum, mask, 32);
|
||||
}
|
||||
amax = warp_reduce_max(amax);
|
||||
sum = warp_reduce_sum(sum);
|
||||
|
||||
const float d = amax / 127;
|
||||
const int8_t q = amax == 0.0f ? 0 : roundf(xi / d);
|
||||
|
|
@ -4801,6 +5107,54 @@ static __device__ __forceinline__ float vec_dot_iq2_xs_q8_1(
|
|||
#endif
|
||||
}
|
||||
|
||||
// TODO
|
||||
static __device__ __forceinline__ float vec_dot_iq2_s_q8_1(
|
||||
const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & iqs) {
|
||||
#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
|
||||
#if QK_K == 256
|
||||
const block_iq2_s * bq2 = (const block_iq2_s *) vbq;
|
||||
|
||||
const int ib32 = iqs;
|
||||
const int8_t * q8 = bq8_1[ib32].qs;
|
||||
const uint8_t * signs = bq2->qs + QK_K/8 + 4*ib32;
|
||||
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 uint32_t * grid = (const uint32_t *)(iq2s_grid + (bq2->qs[4*ib32+l] | ((bq2->qh[ib32] << (8-2*l)) & 0x300)));
|
||||
const uint32_t signs0 = __vcmpeq4(((signs[l] & 0xf) * 0x01010101) & 0x08040201, 0x08040201);
|
||||
const uint32_t signs1 = __vcmpeq4(((signs[l] >> 4) * 0x01010101) & 0x08040201, 0x08040201);
|
||||
const int grid_l = __vsub4(grid[0] ^ signs0, signs0);
|
||||
const int grid_h = __vsub4(grid[1] ^ signs1, signs1);
|
||||
sumi1 = __dp4a(grid_l, *((const int *)q8 + 0), sumi1);
|
||||
sumi1 = __dp4a(grid_h, *((const int *)q8 + 1), sumi1);
|
||||
q8 += 8;
|
||||
}
|
||||
int sumi2 = 0;
|
||||
for (int l = 2; l < 4; ++l) {
|
||||
const uint32_t * grid = (const uint32_t *)(iq2s_grid + (bq2->qs[4*ib32+l] | ((bq2->qh[ib32] << (8-2*l)) & 0x300)));
|
||||
const uint32_t signs0 = __vcmpeq4(((signs[l] & 0xf) * 0x01010101) & 0x08040201, 0x08040201);
|
||||
const uint32_t signs1 = __vcmpeq4(((signs[l] >> 4) * 0x01010101) & 0x08040201, 0x08040201);
|
||||
const int grid_l = __vsub4(grid[0] ^ signs0, signs0);
|
||||
const int grid_h = __vsub4(grid[1] ^ signs1, signs1);
|
||||
sumi2 = __dp4a(grid_l, *((const int *)q8 + 0), sumi2);
|
||||
sumi2 = __dp4a(grid_h, *((const int *)q8 + 1), sumi2);
|
||||
q8 += 8;
|
||||
}
|
||||
const float d = (float)bq2->d * __low2float(bq8_1[ib32].ds) * 0.25f;
|
||||
return d * ((0.5f + ls1) * sumi1 + (0.5f + ls2) * sumi2);
|
||||
#else
|
||||
(void) ksigns64;
|
||||
assert(false);
|
||||
return 0.f;
|
||||
#endif
|
||||
#else
|
||||
(void) ksigns64;
|
||||
assert(false);
|
||||
return 0.f;
|
||||
#endif
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ float vec_dot_iq3_xxs_q8_1(
|
||||
const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & iqs) {
|
||||
#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
|
||||
|
|
@ -4964,6 +5318,76 @@ static __device__ __forceinline__ float vec_dot_iq4_nl_q8_1(
|
|||
return d * (sumi1 + sumi2);
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ float vec_dot_iq4_xs_q8_1(
|
||||
const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & iqs) {
|
||||
|
||||
#if QK_K == 256
|
||||
#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
|
||||
|
||||
const block_iq4_xs * bq4 = (const block_iq4_xs *) vbq;
|
||||
const uint8_t * values = (const uint8_t *)kvalues_iq4nl;
|
||||
|
||||
//// iqs is 0...7
|
||||
//const int ib64 = iqs/2;
|
||||
//const int il = iqs%2;
|
||||
//const int32_t * q8_1 = (const int *)bq8_1[2*ib64+0].qs + 2*il;
|
||||
//const int32_t * q8_2 = (const int *)bq8_1[2*ib64+1].qs + 2*il;
|
||||
//const uint32_t * q4_1 = (const uint32_t *)bq4->qs + 8*ib64 + 2*il;
|
||||
//const uint32_t * q4_2 = q4_1 + 4;
|
||||
//const int8_t ls1 = (bq4->scales_l[ib64] & 0xf) | (((bq4->scales_h >> (4*ib64+0)) & 3) << 4);
|
||||
//const int8_t ls2 = (bq4->scales_l[ib64] >> 4) | (((bq4->scales_h >> (4*ib64+2)) & 3) << 4);
|
||||
//const float d1 = (float)bq4->d * (ls1 - 32) * __low2float(bq8_1[2*ib64+0].ds);
|
||||
//const float d2 = (float)bq4->d * (ls2 - 32) * __low2float(bq8_1[2*ib64+1].ds);
|
||||
//int v1, v2;
|
||||
//int sumi1 = 0, sumi2 = 0;
|
||||
//for (int j = 0; j < 2; ++j) {
|
||||
// get_int_from_table_16(q4_1[j], values, v1, v2);
|
||||
// sumi1 = __dp4a(v2, q8_1[j+4], __dp4a(v1, q8_1[j+0], sumi1));
|
||||
// get_int_from_table_16(q4_2[j], values, v1, v2);
|
||||
// sumi2 = __dp4a(v2, q8_2[j+4], __dp4a(v1, q8_2[j+0], sumi2));
|
||||
//}
|
||||
//return d1 * sumi1 + d2 * sumi2;
|
||||
|
||||
// iqs is 0...7
|
||||
const int ib32 = iqs;
|
||||
const int32_t * q8 = (const int *)bq8_1[ib32].qs;
|
||||
const uint32_t * q4 = (const uint32_t *)bq4->qs + 4*ib32;
|
||||
const int8_t ls = ((bq4->scales_l[ib32/2] >> 4*(ib32%2)) & 0xf) | (((bq4->scales_h >> 2*ib32) & 3) << 4);
|
||||
const float d = (float)bq4->d * (ls - 32) * __low2float(bq8_1[ib32].ds);
|
||||
int v1, v2;
|
||||
int sumi1 = 0, sumi2 = 0;
|
||||
for (int j = 0; j < 4; ++j) {
|
||||
get_int_from_table_16(q4[j], values, v1, v2);
|
||||
sumi1 = __dp4a(v1, q8[j+0], sumi1);
|
||||
sumi2 = __dp4a(v2, q8[j+4], sumi2);
|
||||
}
|
||||
return d * (sumi1 + sumi2);
|
||||
|
||||
//// iqs is 0...15
|
||||
//const int ib32 = iqs/2;
|
||||
//const int il = iqs%2;
|
||||
//const int32_t * q8 = (const int *)bq8_1[ib32].qs + 2*il;
|
||||
//const uint32_t * q4 = (const uint32_t *)bq4->qs + 4*ib32 + 2*il;
|
||||
//const int8_t ls = ((bq4->scales_l[ib32/2] >> 4*(ib32%2)) & 0xf) | (((bq4->scales_h >> 2*ib32) & 3) << 4);
|
||||
//const float d = (float)bq4->d * (ls - 32) * __low2float(bq8_1[ib32].ds);
|
||||
//int v1, v2;
|
||||
//int sumi1 = 0, sumi2 = 0;
|
||||
//for (int j = 0; j < 2; ++j) {
|
||||
// get_int_from_table_16(q4[j], values, v1, v2);
|
||||
// sumi1 = __dp4a(v1, q8[j+0], sumi1);
|
||||
// sumi2 = __dp4a(v2, q8[j+4], sumi2);
|
||||
//}
|
||||
//return d * (sumi1 + sumi2);
|
||||
#else
|
||||
assert(false);
|
||||
return 0.f;
|
||||
#endif
|
||||
#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(
|
||||
|
|
@ -5884,10 +6308,7 @@ static __global__ void dequantize_mul_mat_vec(const void * __restrict__ vx, cons
|
|||
}
|
||||
|
||||
// sum up partial sums and write back result
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
tmp = warp_reduce_sum(tmp);
|
||||
|
||||
if (tid == 0) {
|
||||
#ifdef GGML_CUDA_F16
|
||||
|
|
@ -5937,10 +6358,7 @@ static __global__ void mul_mat_p021_f16_f32(
|
|||
const int idst = channel*nrows_dst + row_dst;
|
||||
|
||||
// sum up partial sums and write back result
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
tmp = warp_reduce_sum(tmp);
|
||||
|
||||
if (threadIdx.x == 0) {
|
||||
dst[idst] = tmp;
|
||||
|
|
@ -5983,10 +6401,7 @@ static __global__ void mul_mat_vec_nc_f16_f32( // nc == non-contiguous
|
|||
}
|
||||
|
||||
// sum up partial sums and write back result
|
||||
#pragma unroll
|
||||
for (int mask = 16; mask > 0; mask >>= 1) {
|
||||
tmp += __shfl_xor_sync(0xffffffff, tmp, mask, 32);
|
||||
}
|
||||
tmp = warp_reduce_sum(tmp);
|
||||
|
||||
if (threadIdx.x == 0) {
|
||||
dst[idst] = tmp;
|
||||
|
|
@ -6997,6 +7412,12 @@ static void dequantize_row_iq2_xs_cuda(const void * vx, dst_t * y, const int k,
|
|||
dequantize_block_iq2_xs<<<nb, 32, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
template<typename dst_t>
|
||||
static void dequantize_row_iq2_s_cuda(const void * vx, dst_t * y, const int k, cudaStream_t stream) {
|
||||
const int nb = k / QK_K;
|
||||
dequantize_block_iq2_s<<<nb, 32, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
template<typename dst_t>
|
||||
static void dequantize_row_iq3_xxs_cuda(const void * vx, dst_t * y, const int k, cudaStream_t stream) {
|
||||
const int nb = k / QK_K;
|
||||
|
|
@ -7021,6 +7442,12 @@ static void dequantize_row_iq4_nl_cuda(const void * vx, dst_t * y, const int k,
|
|||
dequantize_block_iq4_nl<<<nb, 32, 0, stream>>>(vx, y);
|
||||
}
|
||||
|
||||
template<typename dst_t>
|
||||
static void dequantize_row_iq4_xs_cuda(const void * vx, dst_t * y, const int k, cudaStream_t stream) {
|
||||
const int nb = (k + QK_K - 1) / QK_K;
|
||||
dequantize_block_iq4_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;
|
||||
|
|
@ -7058,12 +7485,16 @@ static to_fp16_cuda_t ggml_get_to_fp16_cuda(ggml_type type) {
|
|||
return dequantize_row_iq2_xxs_cuda;
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
return dequantize_row_iq2_xs_cuda;
|
||||
case GGML_TYPE_IQ2_S:
|
||||
return dequantize_row_iq2_s_cuda;
|
||||
case GGML_TYPE_IQ3_XXS:
|
||||
return dequantize_row_iq3_xxs_cuda;
|
||||
case GGML_TYPE_IQ1_S:
|
||||
return dequantize_row_iq1_s_cuda;
|
||||
case GGML_TYPE_IQ4_NL:
|
||||
return dequantize_row_iq4_nl_cuda;
|
||||
case GGML_TYPE_IQ4_XS:
|
||||
return dequantize_row_iq4_xs_cuda;
|
||||
case GGML_TYPE_IQ3_S:
|
||||
return dequantize_row_iq3_s_cuda;
|
||||
case GGML_TYPE_F32:
|
||||
|
|
@ -7099,12 +7530,16 @@ static to_fp32_cuda_t ggml_get_to_fp32_cuda(ggml_type type) {
|
|||
return dequantize_row_iq2_xxs_cuda;
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
return dequantize_row_iq2_xs_cuda;
|
||||
case GGML_TYPE_IQ2_S:
|
||||
return dequantize_row_iq2_s_cuda;
|
||||
case GGML_TYPE_IQ3_XXS:
|
||||
return dequantize_row_iq3_xxs_cuda;
|
||||
case GGML_TYPE_IQ1_S:
|
||||
return dequantize_row_iq1_s_cuda;
|
||||
case GGML_TYPE_IQ4_NL:
|
||||
return dequantize_row_iq4_nl_cuda;
|
||||
case GGML_TYPE_IQ4_XS:
|
||||
return dequantize_row_iq4_xs_cuda;
|
||||
case GGML_TYPE_IQ3_S:
|
||||
return dequantize_row_iq3_s_cuda;
|
||||
case GGML_TYPE_F16:
|
||||
|
|
@ -8166,7 +8601,7 @@ static void * ggml_cuda_pool_malloc_vmm(int device, size_t size, size_t * actual
|
|||
g_cuda_pool_used[device] += size;
|
||||
|
||||
#ifdef DEBUG_CUDA_MALLOC
|
||||
printf("cuda pool[%d]: allocated %llu bytes at %llx [%s]\n", id, (unsigned long long) size, ptr);
|
||||
printf("cuda pool[%d]: allocated %llu bytes at %llx\n", device, (unsigned long long) size, ptr);
|
||||
#endif
|
||||
|
||||
return ptr;
|
||||
|
|
@ -8176,7 +8611,7 @@ static void ggml_cuda_pool_free_vmm(int device, void * ptr, size_t size) {
|
|||
scoped_spin_lock lock(g_cuda_pool_lock);
|
||||
|
||||
#ifdef DEBUG_CUDA_MALLOC
|
||||
printf("cuda pool[%d]: freed %llu bytes at %llx\n", id, (unsigned long long) size, ptr);
|
||||
printf("cuda pool[%d]: freed %llu bytes at %llx\n", device, (unsigned long long) size, ptr);
|
||||
#endif
|
||||
|
||||
g_cuda_pool_used[device] -= size;
|
||||
|
|
@ -8840,9 +9275,11 @@ static int64_t get_row_rounding(ggml_type type, const std::array<float, GGML_CUD
|
|||
case GGML_TYPE_Q6_K:
|
||||
case GGML_TYPE_IQ2_XXS:
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
case GGML_TYPE_IQ2_S:
|
||||
case GGML_TYPE_IQ3_XXS:
|
||||
case GGML_TYPE_IQ1_S:
|
||||
case GGML_TYPE_IQ4_NL:
|
||||
case GGML_TYPE_IQ4_XS:
|
||||
case GGML_TYPE_IQ3_S:
|
||||
return max_compute_capability >= CC_RDNA2 ? 128 : 64;
|
||||
default:
|
||||
|
|
@ -8866,9 +9303,11 @@ static int64_t get_row_rounding(ggml_type type, const std::array<float, GGML_CUD
|
|||
case GGML_TYPE_Q5_K:
|
||||
case GGML_TYPE_IQ2_XXS:
|
||||
case GGML_TYPE_IQ2_XS:
|
||||
case GGML_TYPE_IQ2_S:
|
||||
case GGML_TYPE_IQ3_XXS:
|
||||
case GGML_TYPE_IQ1_S:
|
||||
case GGML_TYPE_IQ4_NL:
|
||||
case GGML_TYPE_IQ4_XS:
|
||||
case GGML_TYPE_IQ3_S:
|
||||
return max_compute_capability >= CC_VOLTA ? 128 : 64;
|
||||
case GGML_TYPE_Q6_K:
|
||||
|
|
@ -8963,6 +9402,10 @@ static void ggml_cuda_op_mul_mat_vec_q(
|
|||
mul_mat_vec_q_cuda<QK_K, QI2_XS, block_iq2_xs, 1, vec_dot_iq2_xs_q8_1>
|
||||
(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, src1_padded_row_size, src1_ncols, nrows_dst, stream);
|
||||
break;
|
||||
case GGML_TYPE_IQ2_S:
|
||||
mul_mat_vec_q_cuda<QK_K, QI2_S, block_iq2_s, 1, vec_dot_iq2_s_q8_1>
|
||||
(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, src1_padded_row_size, src1_ncols, nrows_dst, stream);
|
||||
break;
|
||||
case GGML_TYPE_IQ3_XXS:
|
||||
mul_mat_vec_q_cuda<QK_K, QI3_XXS, block_iq3_xxs, 1, vec_dot_iq3_xxs_q8_1>
|
||||
(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, src1_padded_row_size, src1_ncols, nrows_dst, stream);
|
||||
|
|
@ -8975,6 +9418,10 @@ static void ggml_cuda_op_mul_mat_vec_q(
|
|||
mul_mat_vec_q_cuda<QK4_NL, QI4_NL, block_iq4_nl, VDR_Q4_0_Q8_1_MMVQ, vec_dot_iq4_nl_q8_1>
|
||||
(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, src1_padded_row_size, src1_ncols, nrows_dst, stream);
|
||||
break;
|
||||
case GGML_TYPE_IQ4_XS:
|
||||
mul_mat_vec_q_cuda<QK_K, QI4_XS, block_iq4_xs, 1, vec_dot_iq4_xs_q8_1>
|
||||
(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, src1_padded_row_size, src1_ncols, nrows_dst, stream);
|
||||
break;
|
||||
case GGML_TYPE_IQ3_S:
|
||||
mul_mat_vec_q_cuda<QK_K, QI3_XS, block_iq3_s, 1, vec_dot_iq3_s_q8_1>
|
||||
(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, src1_padded_row_size, src1_ncols, nrows_dst, stream);
|
||||
|
|
@ -11708,7 +12155,8 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
|
|||
}
|
||||
ggml_type a_type = a->type;
|
||||
if (a_type == GGML_TYPE_IQ2_XXS || a_type == GGML_TYPE_IQ2_XS || a_type == GGML_TYPE_IQ3_XXS ||
|
||||
a_type == GGML_TYPE_IQ1_S || a_type == GGML_TYPE_IQ4_NL || a_type == GGML_TYPE_IQ3_S) {
|
||||
a_type == GGML_TYPE_IQ1_S || a_type == GGML_TYPE_IQ4_NL || a_type == GGML_TYPE_IQ3_S ||
|
||||
a_type == GGML_TYPE_IQ2_S || a_type == GGML_TYPE_IQ4_XS) {
|
||||
if (b->ne[1] == 1 && ggml_nrows(b) > 1) {
|
||||
return false;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue