forked from LostRuins/koboldcpp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Makefile
318 lines (262 loc) · 10.1 KB
/
Makefile
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
default: koboldcpp koboldcpp_noavx2 koboldcpp_openblas koboldcpp_openblas_noavx2 koboldcpp_clblast
simple: koboldcpp koboldcpp_noavx2
tools: quantize_gpt2 quantize_gptj quantize_llama quantize_neox
dev: koboldcpp_openblas
ifndef UNAME_S
UNAME_S := $(shell uname -s)
endif
ifndef UNAME_P
UNAME_P := $(shell uname -p)
endif
ifndef UNAME_M
UNAME_M := $(shell uname -m)
endif
ARCH_LINUX1 := $(shell grep "Arch Linux" /etc/os-release 2>/dev/null)
ARCH_LINUX2 := $(shell grep "ID_LIKE=arch" /etc/os-release 2>/dev/null)
ifdef ARCH_LINUX1
ARCH_ADD = -lcblas
endif
ifdef ARCH_LINUX2
ARCH_ADD = -lcblas
endif
CCV := $(shell $(CC) --version | head -n 1)
CXXV := $(shell $(CXX) --version | head -n 1)
# Mac OS + Arm can report x86_64
# ref: https://github.com/ggerganov/whisper.cpp/issues/66#issuecomment-1282546789
ifeq ($(UNAME_S),Darwin)
ifneq ($(UNAME_P),arm)
SYSCTL_M := $(shell sysctl -n hw.optional.arm64 2>/dev/null)
ifeq ($(SYSCTL_M),1)
# UNAME_P := arm
# UNAME_M := arm64
warn := $(warning Your arch is announced as x86_64, but it seems to actually be ARM64. Not fixing that can lead to bad performance. For more info see: https://github.com/ggerganov/whisper.cpp/issues/66\#issuecomment-1282546789)
endif
endif
endif
#
# Compile flags
#
# keep standard at C11 and C++11
CFLAGS = -I. -I./include -I./include/CL -I./otherarch -I./otherarch/tools -Ofast -DNDEBUG -std=c11 -fPIC
CXXFLAGS = -I. -I./examples -I./include -I./include/CL -I./otherarch -I./otherarch/tools -Ofast -DNDEBUG -std=c++11 -fPIC
LDFLAGS =
# these are used on windows, to build some libraries with extra old device compatibility
BONUSCFLAGS1 =
BONUSCFLAGS2 =
OPENBLAS_FLAGS = -DGGML_USE_OPENBLAS -I/usr/local/include/openblas
CLBLAST_FLAGS = -DGGML_USE_CLBLAST
#lets try enabling everything
CFLAGS += -pthread -s
CXXFLAGS += -pthread -s -Wno-multichar
# OS specific
# TODO: support Windows
ifeq ($(UNAME_S),Linux)
CFLAGS += -pthread
CXXFLAGS += -pthread
endif
ifeq ($(UNAME_S),Darwin)
CFLAGS += -pthread
CXXFLAGS += -pthread
endif
ifeq ($(UNAME_S),FreeBSD)
CFLAGS += -pthread
CXXFLAGS += -pthread
endif
ifeq ($(UNAME_S),NetBSD)
CFLAGS += -pthread
CXXFLAGS += -pthread
endif
ifeq ($(UNAME_S),OpenBSD)
CFLAGS += -pthread
CXXFLAGS += -pthread
endif
ifeq ($(UNAME_S),Haiku)
CFLAGS += -pthread
CXXFLAGS += -pthread
endif
# Architecture specific
# TODO: probably these flags need to be tweaked on some architectures
# feel free to update the Makefile for your architecture and send a pull request or issue
ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686))
# Use all CPU extensions that are available:
CFLAGS += -mavx
# old library NEEDS mf16c to work. so we must build with it. new one doesnt
ifeq ($(OS),Windows_NT)
BONUSCFLAGS1 += -mf16c
BONUSCFLAGS2 += -mavx2 -msse3 -mfma
else
# if not on windows, they are clearly building it themselves, so lets just use whatever is supported
CFLAGS += -march=native -mtune=native
endif
endif
ifneq ($(filter ppc64%,$(UNAME_M)),)
POWER9_M := $(shell grep "POWER9" /proc/cpuinfo)
ifneq (,$(findstring POWER9,$(POWER9_M)))
CFLAGS += -mcpu=power9
CXXFLAGS += -mcpu=power9
endif
# Require c++23's std::byteswap for big-endian support.
ifeq ($(UNAME_M),ppc64)
CXXFLAGS += -std=c++23 -DGGML_BIG_ENDIAN
endif
endif
ifndef LLAMA_NO_ACCELERATE
# Mac M1 - include Accelerate framework.
# `-framework Accelerate` works on Mac Intel as well, with negliable performance boost (as of the predict time).
ifeq ($(UNAME_S),Darwin)
CFLAGS += -DGGML_USE_ACCELERATE
LDFLAGS += -framework Accelerate
endif
endif
ifdef LLAMA_CUBLAS
CFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(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
NVCCFLAGS = --forward-unknown-to-host-compiler -arch=native
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
endif
ifdef LLAMA_GPROF
CFLAGS += -pg
CXXFLAGS += -pg
endif
ifdef LLAMA_PERF
CFLAGS += -DGGML_PERF
CXXFLAGS += -DGGML_PERF
endif
ifneq ($(filter aarch64%,$(UNAME_M)),)
# Apple M1, M2, etc.
# Raspberry Pi 3, 4, Zero 2 (64-bit)
CFLAGS +=
CXXFLAGS +=
endif
ifneq ($(filter armv6%,$(UNAME_M)),)
# Raspberry Pi 1, Zero
CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access
endif
ifneq ($(filter armv7%,$(UNAME_M)),)
# Raspberry Pi 2
CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
endif
ifneq ($(filter armv8%,$(UNAME_M)),)
# Raspberry Pi 3, 4, Zero 2 (32-bit)
CFLAGS += -mfp16-format=ieee -mno-unaligned-access
endif
DEFAULT_BUILD =
NOAVX2_BUILD =
OPENBLAS_BUILD =
OPENBLAS_NOAVX2_BUILD =
CLBLAST_BUILD =
ifeq ($(OS),Windows_NT)
DEFAULT_BUILD = $(CXX) $(CXXFLAGS) $^ -shared -o [email protected] $(LDFLAGS)
NOAVX2_BUILD = $(CXX) $(CXXFLAGS) $^ -shared -o [email protected] $(LDFLAGS)
OPENBLAS_BUILD = $(CXX) $(CXXFLAGS) $^ lib/libopenblas.lib -shared -o [email protected] $(LDFLAGS)
OPENBLAS_NOAVX2_BUILD = $(CXX) $(CXXFLAGS) $^ lib/libopenblas.lib -shared -o [email protected] $(LDFLAGS)
CLBLAST_BUILD = $(CXX) $(CXXFLAGS) $^ lib/OpenCL.lib lib/clblast.lib -shared -o [email protected] $(LDFLAGS)
else
DEFAULT_BUILD = $(CXX) $(CXXFLAGS) $^ -shared -o [email protected] $(LDFLAGS)
NOAVX2_BUILD = $(CXX) $(CXXFLAGS) $^ -shared -o [email protected] $(LDFLAGS)
ifdef LLAMA_OPENBLAS
OPENBLAS_BUILD = $(CXX) $(CXXFLAGS) $^ $(ARCH_ADD) -lopenblas -shared -o [email protected] $(LDFLAGS)
OPENBLAS_NOAVX2_BUILD = $(CXX) $(CXXFLAGS) $^ $(ARCH_ADD) -lopenblas -shared -o [email protected] $(LDFLAGS)
endif
ifdef LLAMA_CLBLAST
CLBLAST_BUILD = $(CXX) $(CXXFLAGS) $^ -lclblast -lOpenCL $(ARCH_ADD) -lopenblas -shared -o [email protected] $(LDFLAGS)
endif
ifndef LLAMA_OPENBLAS
ifndef LLAMA_CLBLAST
OPENBLAS_BUILD = @echo 'Your OS $(OS) does not appear to be Windows. For faster speeds, install and link a BLAS library. Set LLAMA_OPENBLAS=1 to compile with OpenBLAS support or LLAMA_CLBLAST=1 to compile with ClBlast support. This is just a reminder, not an error.'
endif
endif
endif
#
# Print build information
#
$(info I llama.cpp build info: )
$(info I UNAME_S: $(UNAME_S))
$(info I UNAME_P: $(UNAME_P))
$(info I UNAME_M: $(UNAME_M))
$(info I CFLAGS: $(CFLAGS))
$(info I CXXFLAGS: $(CXXFLAGS))
$(info I LDFLAGS: $(LDFLAGS))
$(info I CC: $(CCV))
$(info I CXX: $(CXXV))
$(info )
#
# Build library
#
ggml.o: ggml.c ggml.h
$(CC) $(CFLAGS) $(BONUSCFLAGS1) $(BONUSCFLAGS2) -c $< -o $@
ggml_openblas.o: ggml.c ggml.h
$(CC) $(CFLAGS) $(BONUSCFLAGS1) $(BONUSCFLAGS2) $(OPENBLAS_FLAGS) -c $< -o $@
ggml_noavx2.o: ggml.c ggml.h
$(CC) $(CFLAGS) -c $< -o $@
ggml_openblas_noavx2.o: ggml.c ggml.h
$(CC) $(CFLAGS) $(OPENBLAS_FLAGS) -c $< -o $@
ggml-opencl.o: ggml-opencl.c ggml-opencl.h
$(CC) $(CFLAGS) -c $< -o $@
ggml_clblast.o: ggml.c ggml.h
$(CC) $(CFLAGS) $(BONUSCFLAGS1) $(BONUSCFLAGS2) $(CLBLAST_FLAGS) -c $< -o $@
ggml_v1.o: otherarch/ggml_v1.c otherarch/ggml_v1.h
$(CC) $(CFLAGS) $(BONUSCFLAGS1) $(BONUSCFLAGS2) -c $< -o $@
ggml_v1_noavx2.o: otherarch/ggml_v1.c otherarch/ggml_v1.h
$(CC) $(CFLAGS) $(BONUSCFLAGS1) -c $< -o $@
ggml_rwkv.o: otherarch/ggml_rwkv.c otherarch/ggml_rwkv.h
$(CC) $(CFLAGS) $(BONUSCFLAGS1) $(BONUSCFLAGS2) -c $< -o $@
llama.o: llama.cpp llama.h llama-util.h
$(CXX) $(CXXFLAGS) -c $< -o $@
common.o: examples/common.cpp examples/common.h
$(CXX) $(CXXFLAGS) -c $< -o $@
expose.o: expose.cpp expose.h
$(CXX) $(CXXFLAGS) -c $< -o $@
gpttype_adapter.o: gpttype_adapter.cpp
$(CXX) $(CXXFLAGS) -c $< -o $@
clean:
rm -vf *.o main quantize_llama quantize_gpt2 quantize_gptj quantize_neox quantize-stats perplexity embedding benchmark-matmult save-load-state build-info.h main.exe quantize_llama.exe quantize_gptj.exe quantize_gpt2.exe quantize_neox.exe koboldcpp.dll koboldcpp_openblas.dll koboldcpp_noavx2.dll koboldcpp_openblas_noavx2.dll koboldcpp_clblast.dll koboldcpp.so koboldcpp_openblas.so koboldcpp_noavx2.so koboldcpp_openblas_noavx2.so koboldcpp_clblast.so gptj.exe gpt2.exe
#
# Examples
#
main: examples/main/main.cpp build-info.h ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
@echo
@echo '==== Run ./main -h for help. ===='
@echo
koboldcpp: ggml.o ggml_rwkv.o ggml_v1.o expose.o common.o gpttype_adapter.o
$(DEFAULT_BUILD)
koboldcpp_openblas: ggml_openblas.o ggml_rwkv.o ggml_v1.o expose.o common.o gpttype_adapter.o
$(OPENBLAS_BUILD)
koboldcpp_noavx2: ggml_noavx2.o ggml_rwkv.o ggml_v1_noavx2.o expose.o common.o gpttype_adapter.o
$(NOAVX2_BUILD)
koboldcpp_openblas_noavx2: ggml_openblas_noavx2.o ggml_rwkv.o ggml_v1_noavx2.o expose.o common.o gpttype_adapter.o
$(OPENBLAS_NOAVX2_BUILD)
koboldcpp_clblast: ggml_clblast.o ggml_rwkv.o ggml_v1.o expose.o common.o gpttype_adapter.o ggml-opencl.o
$(CLBLAST_BUILD)
quantize_llama: examples/quantize/quantize.cpp ggml.o llama.o
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
quantize_gptj: ggml.o llama.o otherarch/tools/gptj_quantize.cpp otherarch/tools/common-ggml.cpp
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
quantize_gpt2: ggml.o llama.o otherarch/tools/gpt2_quantize.cpp otherarch/tools/common-ggml.cpp
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
quantize_neox: ggml.o llama.o otherarch/tools/neox_quantize.cpp otherarch/tools/common-ggml.cpp
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
quantize-stats: examples/quantize-stats/quantize-stats.cpp ggml.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
perplexity: examples/perplexity/perplexity.cpp ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
embedding: examples/embedding/embedding.cpp ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
libllama.so: llama.o ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
#
# Tests
#
benchmark-matmult: examples/benchmark/benchmark-matmult.cpp ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
./$@
.PHONY: tests
tests:
bash ./tests/run-tests.sh