tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-22 10:48:12 +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

13
vulkan-shaders/dequant_head.comp Normal file
View File

@ -0,0 +1,13 @@
#extension GL_EXT_control_flow_attributes : require
#extension GL_EXT_shader_16bit_storage : require
layout (push_constant) uniform parameter
{
uint M;
uint K;
uint stride_a;
uint stride_b;
uint nel;
} p;
#include "types.comp"