tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-16 23:57:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Vulkan Shader Refactor, Memory Debugging Option (#7947)

Browse Source 
* 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
This commit is contained in:
0cc4m
2024-06-16 07:17:31 +02:00
committed by GitHub
parent 0c7b3595b9
commit 7c7836d9d4
54 changed files with 25266 additions and 21885 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vulkan-shaders/div.comp Normal file
View File

@ -0,0 +1,12 @@
#version 450
#include "types.comp"
#include "generic_binary_head.comp"
void main() {
if (gl_GlobalInvocationID.x >= p.ne) {
return;
}
data_d[p.d_offset + dst_idx(gl_GlobalInvocationID.x)] = D_TYPE(FLOAT_TYPE(data_a[src0_idx(gl_GlobalInvocationID.x)]) / FLOAT_TYPE(data_b[src1_idx(gl_GlobalInvocationID.x)]));
}