mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
* 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
1.2 KiB
1.2 KiB