From 7fc50c051ae8a78e9643fdf172d12e20f2dd9b6c Mon Sep 17 00:00:00 2001
From: slaren <2141330+slaren@users.noreply.github.com>
Date: Sat, 29 Apr 2023 02:04:18 +0200
Subject: cuBLAS: use host pinned memory and dequantize while copying (#1207)

* cuBLAS: dequantize simultaneously while copying memory

* cuBLAS: use host pinned memory

* cuBLAS: improve ggml_compute_forward_mul_mat_f16_f32 with pinned memory

* cuBLAS: also pin kv cache

* fix rebase
---
 Makefile | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'Makefile')

diff --git a/Makefile b/Makefile
index 0715e85..5a1cb3e 100644
--- a/Makefile
+++ b/Makefile
@@ -106,6 +106,7 @@ ifdef LLAMA_OPENBLAS
 endif
 ifdef LLAMA_CUBLAS
 	CFLAGS    += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
+	CXXFLAGS  += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(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
@@ -164,10 +165,10 @@ $(info )
 # Build library
 #
 
-ggml.o: ggml.c ggml.h
+ggml.o: ggml.c ggml.h ggml-cuda.h
 	$(CC)  $(CFLAGS)   -c $< -o $@
 
-llama.o: llama.cpp ggml.h llama.h llama_util.h
+llama.o: llama.cpp ggml.h ggml-cuda.h llama.h llama_util.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 
 common.o: examples/common.cpp examples/common.h
-- 
cgit v1.2.3