mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-15 04:33:06 -04:00
* 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