Michael Yang bab6f34dc0 ml/backend/ggml: update model loading for hybrid/multi backends ... use a similar strategy as llama.cpp for deciding where tensors should be allocated. this will be improved later to be aware of usable memory before assigning the tensor		2025-03-07 14:08:21 -08:00
..
backend	ml/backend/ggml: update model loading for hybrid/multi backends	2025-03-07 14:08:21 -08:00
nn	attention: Remove unnecessary contiguous operations	2025-03-01 20:53:23 -08:00
backend.go	ml/backend/ggml: consolidate system info logging	2025-03-04 15:14:31 -08:00