David Huang 84778e9770 CUDA/HIP: Share the same unified memory allocation logic. (#12934) ... Replace compile-time `GGML_HIP_UMA` with environment variable `GGML_CUDA_ENABLE_UNIFIED_MEMORY`. This unifies the usage on NVIDIA and AMD GPUs, and allows a single binary to be shared between integrated and dedicated GPUs.		2025-04-15 11:20:38 +02:00
..
cmake	scripts : update sync + fix cmake merge	2025-03-27 10:09:29 +02:00
include	ggml : add bilinear upscale support (ggml/1185)	2025-04-11 00:17:47 +03:00
src	CUDA/HIP: Share the same unified memory allocation logic. (#12934)	2025-04-15 11:20:38 +02:00
.gitignore	vulkan : cmake integration (#8119)	2024-07-13 18:12:39 +02:00
CMakeLists.txt	CUDA/HIP: Share the same unified memory allocation logic. (#12934)	2025-04-15 11:20:38 +02:00