tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA/HIP: Share the same unified memory allocation logic. (#12934)

Browse Source 
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.
This commit is contained in:
David Huang
2025-04-15 17:20:38 +08:00
committed by GitHub
parent 510676475f
commit 84778e9770
6 changed files with 22 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Makefile
View File

@ -780,10 +780,6 @@ ifdef GGML_HIP
MK_CPPFLAGS += -DGGML_USE_HIP -DGGML_USE_CUDA
ifdef GGML_HIP_UMA
MK_CPPFLAGS += -DGGML_HIP_UMA
endif # GGML_HIP_UMA
MK_LDFLAGS += -L$(ROCM_PATH)/lib -Wl,-rpath=$(ROCM_PATH)/lib
MK_LDFLAGS += -L$(ROCM_PATH)/lib64 -Wl,-rpath=$(ROCM_PATH)/lib64
MK_LDFLAGS += -lhipblas -lamdhip64 -lrocblas