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

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
54 changed files with 25266 additions and 21885 deletions
Download patch file Download diff file Expand all files Collapse all files

5
CMakeLists.txt
View file

@ -119,6 +119,7 @@ option(LLAMA_HIP_UMA "llama: use HIP unified memory arch
option(LLAMA_VULKAN "llama: use Vulkan" OFF)
option(LLAMA_VULKAN_CHECK_RESULTS "llama: run Vulkan op checks" OFF)
option(LLAMA_VULKAN_DEBUG "llama: enable Vulkan debug output" OFF)
option(LLAMA_VULKAN_MEMORY_DEBUG "llama: enable Vulkan memory debug output" OFF)
option(LLAMA_VULKAN_VALIDATE "llama: enable Vulkan validation" OFF)
option(LLAMA_VULKAN_RUN_TESTS "llama: run Vulkan tests" OFF)
option(LLAMA_METAL "llama: use Metal" ${LLAMA_METAL_DEFAULT})
@ -534,6 +535,10 @@ if (LLAMA_VULKAN)
add_compile_definitions(GGML_VULKAN_DEBUG)
endif()
if (LLAMA_VULKAN_MEMORY_DEBUG)
add_compile_definitions(GGML_VULKAN_MEMORY_DEBUG)
endif()
if (LLAMA_VULKAN_VALIDATE)
add_compile_definitions(GGML_VULKAN_VALIDATE)
endif()