mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-03-03 02:20:01 +00:00
19c57dbe1d
* It compiles * Seems to be working with coopmat * Vulkan needs f32 precision for flash attention * Vulkan: fix u_batch > 4096/n_active_experts for coopmat1. Without this fix we get an assert. We get the same assert in mainline too. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
16 lines
402 B
Plaintext
16 lines
402 B
Plaintext
#extension GL_EXT_shader_16bit_storage : require
|
|
|
|
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout (binding = 0) readonly buffer A {A_TYPE data_a[];};
|
|
layout (binding = 1) readonly buffer B {A_TYPE data_b[];};
|
|
layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};
|
|
|
|
layout (push_constant) uniform parameter
|
|
{
|
|
uint N;
|
|
uint ne00;
|
|
uint ne20;
|
|
uint mode;
|
|
} p;
|