Update Makefile

Makefile

@@ -104,8 +104,8 @@ HIP_INCLUDE := -I $(ROOT_DIR)/csrc -I $(ROOT_DIR)/include
 HIP_LIB := -L$(DTK_PATH)/lib -L$(DTK_PATH)/llvm/bin/../lib/clang/14.0.0/lib/linux -L/opt/rh/devtoolset-7/root/usr/lib/gcc/x86_64-redhat-linux/7 -L/opt/rh/devtoolset-7/root/usr/lib/gcc/x86_64-redhat-linux/7/../../../../lib64 -L/lib/x86_64-linux-gnu -L/lib/../lib64 -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib64 -L/lib -L/usr/lib -lgcc_s -lgcc -lpthread -lm -lrt -lamdhip64 -lhipblas -lhipsparse -lclang_rt.builtins-x86_64 -lstdc++ -lm -lgcc_s -lgcc -lc -lgcc_s -lgcc
 
 hip: $(BUILD_DIR)
-	$(DTK_PATH)/bin/hipcc -std=c++14 -c -fPIC --amdgpu-target=gfx906 --gpu-max-threads-per-block=1024 --offload-arch=gfx906 $(HIP_INCLUDE) -o $(BUILD_DIR)/ops.o -D NO_CUBLASLT $(CSRC)/ops.cu
-	$(DTK_PATH)/bin/hipcc -std=c++14 -c -fPIC --amdgpu-target=gfx906 --gpu-max-threads-per-block=1024 --offload-arch=gfx906 $(HIP_INCLUDE) -o $(BUILD_DIR)/kernels.o -D NO_CUBLASLT $(CSRC)/kernels.cu
+	$(DTK_PATH)/bin/hipcc -std=c++14 -c -fPIC --offload-arch=gfx906 $(HIP_INCLUDE) -o $(BUILD_DIR)/ops.o -D NO_CUBLASLT $(CSRC)/ops.cu
+	$(DTK_PATH)/bin/hipcc -std=c++14 -c -fPIC --offload-arch=gfx906 $(HIP_INCLUDE) -o $(BUILD_DIR)/kernels.o -D NO_CUBLASLT $(CSRC)/kernels.cu
 	# /usr/bin/hipcc -fPIC -static $(BUILD_DIR)/ops.o $(BUILD_DIR)/kernels.o -o $(BUILD_DIR)/link.so 
 	$(GPP) -std=c++14 -D__HIP_PLATFORM_AMD__ -DBUILD_CUDA -shared -fPIC -I $(DTK_PATH)/include $(HIP_INCLUDE) $(BUILD_DIR)/ops.o $(BUILD_DIR)/kernels.o $(FILES_CPP) $(HIP_LIB) -o ./bitsandbytes/libbitsandbytes_hip_nocublaslt.so