vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

vulkan : implement Stable Diffusion operators (ggml/904)

Browse source 
* Fix Vulkan repeat op

* Implement Vulkan concat op

* Delete old Vulkan shader generator

* Implement Vulkan im2col op

* Implement Vulkan unary gelu_quick op

* Implement Vulkan group_norm op

* Implement Vulkan timestep_embedding op

* Implement Vulkan upscale op

* Fix Vulkan vk_context tensor extra index issue

* Fix Vulkan matmul shader parameter bug

* Properly fix Vulkan matmul shader parameter bug

* Add Vulkan ADD f16 + f32 -> f16 operator support

* Implement Vulkan tanh op

* Fix Vulkan group count too large Validation error on non-Nvidia GPUs

* Throw error when too much memory is requested

* Fix another Vulkan group count too large Validation error on non-Nvidia GPUs

* Fix matmul MMQ condition

* Implement Vulkan pad op

* Fix Vulkan crash when tensor is used multiple times in a compute graph

* Add Vulkan CONCAT f16 + f16 -> f16 op

* Add Vulkan LEAKY_RELU op
This commit is contained in:
0cc4m 2024-08-04 17:28:08 +02:00 • committed by Georgi Gerganov
parent 655858ace0
commit a3738b2fa7
28 changed files with 1032 additions and 293 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml/src/vulkan-shaders/generic_binary_head.comp
View file

@ -7,7 +7,7 @@ layout (push_constant) uniform parameter
uint ne10; uint ne11; uint ne12; uint ne13; uint nb10; uint nb11; uint nb12; uint nb13;
uint ne20; uint ne21; uint ne22; uint ne23; uint nb20; uint nb21; uint nb22; uint nb23;
uint d_offset;
float param1; float param2;
float param1; float param2; int param3;
} p;
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
@ -16,6 +16,10 @@ layout (binding = 0) readonly buffer A {A_TYPE data_a[];};
layout (binding = 1) readonly buffer B {B_TYPE data_b[];};
layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};
uint get_idx() {
return gl_GlobalInvocationID.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
}
uint src0_idx(uint idx) {
const uint i03 = idx / (p.ne02*p.ne01*p.ne00);
const uint i03_offset = i03 * p.ne02*p.ne01*p.ne00;