mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-13 10:57:15 +00:00
438a83926a
* vulkan: implement specialized MMV kernels for IQ2 quantizations * vulkan: add MMV kernels for IQ3 quants * vulkan: Increase MMV batch size and unroll IQ LUT setup * vulkan: fix init_iq_shmem for WG sizes larger than tables * vulkan: common batch size for all I-quants
42 lines
1.2 KiB
Plaintext
42 lines
1.2 KiB
Plaintext
#version 450
|
|
|
|
#extension GL_EXT_control_flow_attributes : enable
|
|
|
|
#include "types.comp"
|
|
#include "generic_binary_head.comp"
|
|
#include "dequant_funcs.comp"
|
|
|
|
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
void main() {
|
|
const uint i00 = (gl_GlobalInvocationID.x)*2;
|
|
const uint i10 = gl_GlobalInvocationID.y;
|
|
const uint i11 = (gl_GlobalInvocationID.z)/p.ne12;
|
|
const uint i12 = (gl_GlobalInvocationID.z)%p.ne12;
|
|
|
|
#ifdef NEEDS_INIT_IQ_SHMEM
|
|
init_iq_shmem(gl_WorkGroupSize);
|
|
#endif
|
|
|
|
if (i00 >= p.ne00) {
|
|
return;
|
|
}
|
|
|
|
const uint i01 = data_b[i10*p.nb10 + i11*p.nb11 + i12*p.nb12];
|
|
|
|
const uint a_offset = i01*p.nb01 + i11*p.nb02 + i12*p.nb03;
|
|
const uint d_offset = i10*p.nb21 + i11*p.nb22 + i12*p.nb23;
|
|
|
|
const uint ib = a_offset + i00/QUANT_K; // block index
|
|
const uint iqs = (i00%QUANT_K)/QUANT_R; // quant index
|
|
const uint iybs = i00 - i00%QUANT_K; // dst block start index
|
|
const uint y_offset = QUANT_R == 1 ? 1 : QUANT_K/2;
|
|
|
|
vec2 v = dequantize(ib, iqs, 0);
|
|
const vec2 dm = get_dm(ib, 0);
|
|
v = v * dm.x + dm.y;
|
|
|
|
data_d[d_offset + iybs + iqs ] = D_TYPE(v.x);
|
|
data_d[d_offset + iybs + iqs + y_offset] = D_TYPE(v.y);
|
|
}
|