Aaron Teo 046d5fd44e llama: use host memory if device reports 0 memory (#18587)		2026-01-09 05:34:56 +08:00
..
cmake
include	ggml-webgpu: Fix GGML_MEM_ALIGN to 8 for emscripten. (#18628)	2026-01-08 08:36:42 -08:00
src	llama: use host memory if device reports 0 memory (#18587)	2026-01-09 05:34:56 +08:00
.gitignore
CMakeLists.txt