make : support customized LLAMA_CUDA_NVCC and LLAMA_CUDA_CCBIN (#2275)

Under certain environment, nvcc and gcc is installed under customized path but not standard path

Co-authored-by: Yan Lin <redacted>

diff --git a/Makefile b/Makefile
index 61f2c77ab9932fe31d4e29d18c9e689418d62ff6..5aa0ded3dc9be7a19c950dbd38a8bf1116bb439b 100644 (file)
--- a/Makefile
+++ b/Makefile
@@ -193,8 +193,12 @@ ifdef LLAMA_CUBLAS
        CXXFLAGS  += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
        LDFLAGS   += -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib
        OBJS      += ggml-cuda.o
-       NVCC      = nvcc
        NVCCFLAGS = --forward-unknown-to-host-compiler
+ifdef LLAMA_CUDA_NVCC
+       NVCC = $(LLAMA_CUDA_NVCC)
+else
+       NVCC = nvcc
+endif #LLAMA_CUDA_NVCC
 ifdef CUDA_DOCKER_ARCH
        NVCCFLAGS += -Wno-deprecated-gpu-targets -arch=$(CUDA_DOCKER_ARCH)
 else
@@ -223,7 +227,9 @@ ifdef LLAMA_CUDA_KQUANTS_ITER
 else
        NVCCFLAGS += -DK_QUANTS_PER_ITERATION=2
 endif
-
+ifdef LLAMA_CUDA_CCBIN
+    NVCCFLAGS += -ccbin $(LLAMA_CUDA_CCBIN)
+endif
 ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
        $(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
 endif # LLAMA_CUBLAS