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
..
backend	sycl: update documentation to use -no-cnv (#12845)	2025-04-09 11:22:04 +02:00
development	repo : update links to new url (#11886)	2025-02-15 16:40:57 +02:00
android.md	repo : update links to new url (#11886)	2025-02-15 16:40:57 +02:00
build.md	CUDA/HIP: Share the same unified memory allocation logic. (#12934)	2025-04-15 11:20:38 +02:00
docker.md	repo : update links to new url (#11886)	2025-02-15 16:40:57 +02:00
function-calling.md	update function-calling.md w/ template override for functionary-small-v3.2 (#12214)	2025-03-06 09:03:31 +00:00
install.md	install : add macports (#12518)	2025-03-23 10:21:48 +02:00
llguidance.md	llguidance build fixes for Windows (#11664)	2025-02-14 12:46:08 -08:00