aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-09-19 19:13:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

make : fix PERF build with cuBLAS

Browse source
This commit is contained in:
Georgi Gerganov 2023-05-13 17:25:09 +03:00
parent 5a5aeb1e91
commit bda4d7c215
1 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
Makefile
View file

@ -74,6 +74,15 @@ ifeq ($(UNAME_S),Haiku)
CXXFLAGS += -pthread CXXFLAGS += -pthread
endif endif
ifdef LLAMA_GPROF
CFLAGS += -pg
CXXFLAGS += -pg
endif
ifdef LLAMA_PERF
CFLAGS += -DGGML_PERF
CXXFLAGS += -DGGML_PERF
endif
# Architecture specific # Architecture specific
# TODO: probably these flags need to be tweaked on some architectures # TODO: probably these flags need to be tweaked on some architectures
# feel free to update the Makefile for your architecture and send a pull request or issue # feel free to update the Makefile for your architecture and send a pull request or issue
@ -135,14 +144,6 @@ ifdef LLAMA_CLBLAST
ggml-opencl.o: ggml-opencl.c ggml-opencl.h ggml-opencl.o: ggml-opencl.c ggml-opencl.h
$(CC) $(CFLAGS) -c $< -o $@ $(CC) $(CFLAGS) -c $< -o $@
endif endif
ifdef LLAMA_GPROF
CFLAGS += -pg
CXXFLAGS += -pg
endif
ifdef LLAMA_PERF
CFLAGS += -DGGML_PERF
CXXFLAGS += -DGGML_PERF
endif
ifneq ($(filter aarch64%,$(UNAME_M)),) ifneq ($(filter aarch64%,$(UNAME_M)),)
# Apple M1, M2, etc. # Apple M1, M2, etc.
# Raspberry Pi 3, 4, Zero 2 (64-bit) # Raspberry Pi 3, 4, Zero 2 (64-bit)