llama.cpp/vulkan-shaders/dequant_q8_0.comp
0cc4m 7c7836d9d4
Vulkan Shader Refactor, Memory Debugging Option (#7947)
* Refactor shaders, extract GLSL code from ggml_vk_generate_shaders.py into vulkan-shaders directory

* Improve debug log code

* Add memory debug output option

* Fix flake8

* Fix unnecessary high llama-3 VRAM use
2024-06-16 07:17:31 +02:00

32 lines
839 B
Plaintext

#version 450
#include "dequant_head.comp"
layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
layout (binding = 0) readonly buffer A {block_q8_0 data_a[];};
layout (binding = 1) writeonly buffer D {D_TYPE data_b[];};
void main() {
const uint i = gl_WorkGroupID.x * 4 + gl_LocalInvocationID.x / 64;
const uint tid = gl_LocalInvocationID.x % 64;
const uint il = tid/32;
const uint ir = tid%32;
const uint ib = 32*i + ir;
if (ib >= p.nel / 32) {
return;
}
const uint b_idx = 1024*i + 32*ir + 16*il;
const float d = float(data_a[ib].d);
const uint q_idx = 16*il;
[[unroll]] for (uint l = 0; l < 16; l += 2) {
data_b[b_idx + l ] = D_TYPE(d * data_a[ib].qs[q_idx + l ]);
data_b[b_idx + l + 1] = D_TYPE(d * data_a[ib].qs[q_idx + l + 1]);
}
}