mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-13 10:57:15 +00:00
* vulkan: implement GGML_OP_ROPE_BACK * vulkan: implement GGML_OP_RMS_NORM_BACK * vulkan: implement GGML_OP_SILU_BACK * vulkan: implement GGML_OP_SOFTMAX_BACK
27 lines
761 B
Plaintext
27 lines
761 B
Plaintext
#version 450
|
|
|
|
#include "generic_head.comp"
|
|
#include "types.comp"
|
|
|
|
#extension GL_EXT_control_flow_attributes : enable
|
|
|
|
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout (binding = 0) readonly buffer G {A_TYPE data_g[];};
|
|
layout (binding = 1) readonly buffer X {B_TYPE data_x[];};
|
|
layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};
|
|
|
|
void main() {
|
|
const uint i = gl_GlobalInvocationID.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
|
|
|
|
if (i >= p.KX) {
|
|
return;
|
|
}
|
|
|
|
// Compute derivative of SiLU(x): 1/(1+exp(-x)) - x*exp(-x)/(1+exp(-x))^2
|
|
|
|
const float xi = float(data_x[i]);
|
|
const float s = 1.0f / (1.0f + exp(-xi));
|
|
data_d[i] = D_TYPE(data_g[i] * (s + xi * s * (1 - s)));
|
|
}
|