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

move BLAS to a separate backend (#6210)

Browse Source 
* move BLAS to a separate backend

* rename GGML_USE_OPENBLAS to GGML_USE_BLAS

* alloc : reuse same buffer when the same buffer type if used multiple times

* set number of threads automatically for openblas and blis

* sched : print assignments when GGML_SCHED_DEBUG env variable is set

* sched : allow ops with weights on an incompatible buffer type

This will cause the weight to be copied to a backend that supports the
op, which is very costly. The weight should have been stored in a buffer
of a backend that can run the op, but llama.cpp cannot do this
automatically at the moment.

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
slaren
2024-06-13 03:11:35 +02:00
committed by GitHub
parent 1c641e6aac
commit f578b86b21
17 changed files with 821 additions and 379 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
Makefile
View File

@ -440,10 +440,11 @@ ifndef LLAMA_NO_ACCELERATE
# Mac OS - include Accelerate framework.
# `-framework Accelerate` works both with Apple Silicon and Mac Intel
ifeq ($(UNAME_S),Darwin)
MK_CPPFLAGS += -DGGML_USE_ACCELERATE
MK_CPPFLAGS += -DGGML_USE_ACCELERATE -DGGML_USE_BLAS
MK_CPPFLAGS += -DACCELERATE_NEW_LAPACK
MK_CPPFLAGS += -DACCELERATE_LAPACK_ILP64
MK_LDFLAGS += -framework Accelerate
OBJS += ggml-blas.o
endif
endif # LLAMA_NO_ACCELERATE
@ -454,21 +455,30 @@ ifndef LLAMA_NO_OPENMP
endif # LLAMA_NO_OPENMP
ifdef LLAMA_OPENBLAS
MK_CPPFLAGS += -DGGML_USE_OPENBLAS $(shell pkg-config --cflags-only-I openblas)
MK_CPPFLAGS += -DGGML_USE_BLAS $(shell pkg-config --cflags-only-I openblas)
MK_CFLAGS += $(shell pkg-config --cflags-only-other openblas)
MK_LDFLAGS += $(shell pkg-config --libs openblas)
OBJS += ggml-blas.o
endif # LLAMA_OPENBLAS
ifdef LLAMA_OPENBLAS64
MK_CPPFLAGS += -DGGML_USE_BLAS $(shell pkg-config --cflags-only-I openblas64)
MK_CFLAGS += $(shell pkg-config --cflags-only-other openblas64)
MK_LDFLAGS += $(shell pkg-config --libs openblas64)
OBJS += ggml-blas.o
endif # LLAMA_OPENBLAS64
ifdef LLAMA_BLIS
MK_CPPFLAGS += -DGGML_USE_BLAS -I/usr/local/include/blis -I/usr/include/blis
MK_LDFLAGS += -lblis -L/usr/local/lib
OBJS += ggml-blas.o
endif # LLAMA_BLIS
ifndef LLAMA_NO_LLAMAFILE
MK_CPPFLAGS += -DGGML_USE_LLAMAFILE
OBJS += sgemm.o
endif
ifdef LLAMA_BLIS
MK_CPPFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/blis -I/usr/include/blis
MK_LDFLAGS += -lblis -L/usr/local/lib
endif # LLAMA_BLIS
ifdef LLAMA_RPC
MK_CPPFLAGS += -DGGML_USE_RPC
OBJS += ggml-rpc.o
@ -776,6 +786,9 @@ ggml-backend.o: ggml-backend.c ggml.h ggml-backend.h
ggml-quants.o: ggml-quants.c ggml.h ggml-quants.h ggml-common.h
$(CC) $(CFLAGS) -c $< -o $@
ggml-blas.o: ggml-blas.cpp ggml-blas.h
$(CXX) $(CXXFLAGS) -c $< -o $@
unicode.o: unicode.cpp unicode.h
$(CXX) $(CXXFLAGS) -c $< -o $@