llama.cpp/generic_head.comp at 083bacce14c1aaf9976aa40e8266cdc25ac749d3 - llama.cpp - Cat's Mantra

tqcq/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00

Files

0cc4m 7c7836d9d4 Vulkan Shader Refactor, Memory Debugging Option (#7947 )

* 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

2024-06-16 07:17:31 +02:00

10 lines

160 B

Plaintext

Raw Blame History

 #extension GL_EXT_shader_16bit_storage : require
 layout (push_constant) uniform parameter
 {
     uint KX;
     uint KY;
     float param1;
     float param2;
 } p;