Work in progress

Makefile

@@ -2,9 +2,12 @@ ifndef LLAMA_MAKEFILE
 $(error The Makefile build is deprecated. Use the CMake build instead. For more details, see https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md)
 endif
 
+# Modified by Brad Hutchings to build llama.cpp targets correctly and build with cosmocc.
+
 # Define the default target now so that it is always the first target
 BUILD_TARGETS = \
 	libllava.a \
+	llama-server \
 	llama-batched \
 	llama-batched-bench \
 	llama-bench \
@@ -36,7 +39,6 @@ BUILD_TARGETS = \
 	llama-quantize-stats \
 	llama-retrieval \
 	llama-save-load-state \
-	llama-server \
 	llama-simple \
 	llama-simple-chat \
 	llama-run \
@@ -258,7 +260,7 @@ endif
 #
 
 # keep standard at C11 and C++17
-MK_CPPFLAGS  = -Iggml/include -Iggml/src -Iinclude -Isrc -Icommon -DGGML_USE_CPU
+MK_CPPFLAGS  = -Iggml/include -Iggml/src -Iinclude -Isrc -Icommon -I. -DGGML_USE_CPU
 MK_CFLAGS    = -std=c11   -fPIC
 MK_CXXFLAGS  = -std=c++17 -fPIC
 MK_NVCCFLAGS = -std=c++17
@@ -370,37 +372,78 @@ ifndef GGML_NO_CPU_AARCH64
 	MK_CPPFLAGS += -DGGML_USE_CPU_AARCH64
 endif
 
-# warnings
-WARN_FLAGS = \
-	-Wall \
-	-Wextra \
-	-Wpedantic \
-	-Wcast-qual \
-	-Wno-unused-function
-
-MK_CFLAGS += \
-	$(WARN_FLAGS) \
-	-Wshadow \
-	-Wstrict-prototypes \
-	-Wpointer-arith \
-	-Wmissing-prototypes \
-	-Werror=implicit-int \
-	-Werror=implicit-function-declaration
-
-MK_CXXFLAGS += \
-	$(WARN_FLAGS) \
-	-Wmissing-declarations \
-	-Wmissing-noreturn
+ifeq ($(UNAME_S),cosmocc)
+$(info Setting MK_CFLAGS and MK_CXXFLAGS flags for cosmocc.)
+
+	WARN_FLAGS_ORIG = \
+		-Wall \
+		-Wextra \
+		-Wpedantic \
+		-Wcast-qual \
+		-Wno-unused-function
+
+	WARN_FLAGS = \
+		-Wcast-qual \
+		-Wno-unused-function
+
+	MK_CFLAGS += \
+		$(WARN_FLAGS) \
+		-Wshadow \
+		-Wstrict-prototypes \
+		-Wpointer-arith \
+		-Wmissing-prototypes \
+		-Werror=implicit-function-declaration \
+		-Wno-implicit-int \
+		-DCOSMOCC=1
+
+	MK_CXXFLAGS += \
+		$(WARN_FLAGS) \
+		-Wmissing-declarations \
+		-Wmissing-noreturn \
+		-Wno-literal-suffix \
+		-DCOSMOCC=1
+
+
+else
+$(info Using default MK_CFLAGS and MK_CXXFLAGS flags.)
+
+	# warnings
+	WARN_FLAGS = \
+		-Wall \
+		-Wextra \
+		-Wpedantic \
+		-Wcast-qual \
+		-Wno-unused-function
+
+	MK_CFLAGS += \
+		$(WARN_FLAGS) \
+		-Wshadow \
+		-Wstrict-prototypes \
+		-Wpointer-arith \
+		-Wmissing-prototypes \
+		-Werror=implicit-int \
+		-Werror=implicit-function-declaration
+
+	MK_CXXFLAGS += \
+		$(WARN_FLAGS) \
+		-Wmissing-declarations \
+		-Wmissing-noreturn
+
+endif
+
+
 
 ifeq ($(LLAMA_FATAL_WARNINGS),1)
 	MK_CFLAGS   += -Werror
 	MK_CXXFLAGS += -Werror
 endif
 
 # this version of Apple ld64 is buggy
+ifneq ($(UNAME_S),cosmocc)
 ifneq '' '$(findstring dyld-1015.7,$(shell $(CC) $(LDFLAGS) -Wl,-v 2>&1))'
 	MK_CPPFLAGS += -DHAVE_BUGGY_APPLE_LINKER
 endif
+endif
 
 # OS specific
 # TODO: support Windows
@@ -460,6 +503,7 @@ ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686 amd64))
 	#MK_CXXFLAGS += -mssse3
 endif
 
+ifneq ($(UNAME_S),cosmocc)
 ifneq '' '$(findstring mingw,$(shell $(CC) -dumpmachine))'
 	# The stack is only 16-byte aligned on Windows, so don't let gcc emit aligned moves.
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54412
@@ -470,6 +514,7 @@ ifneq '' '$(findstring mingw,$(shell $(CC) -dumpmachine))'
 	# Target Windows 8 for PrefetchVirtualMemory
 	MK_CPPFLAGS += -D_WIN32_WINNT=0x602
 endif
+endif
 
 ifneq ($(filter aarch64%,$(UNAME_M)),)
 	# Apple M1, M2, etc.
@@ -978,16 +1023,33 @@ OBJ_GGML = \
 	$(DIR_GGML)/src/ggml-cpu/ggml-cpu-hbm.o \
 	$(DIR_GGML)/src/ggml-cpu/ggml-cpu-quants.o \
 	$(DIR_GGML)/src/ggml-cpu/ggml-cpu-traits.o \
+	$(DIR_GGML)/src/gguf.o \
 	$(OBJ_GGML_EXT)
 
 OBJ_LLAMA = \
 	$(DIR_LLAMA)/llama.o \
 	$(DIR_LLAMA)/llama-vocab.o \
 	$(DIR_LLAMA)/llama-grammar.o \
 	$(DIR_LLAMA)/llama-sampling.o \
+	$(DIR_LLAMA)/llama-adapter.o \
+	$(DIR_LLAMA)/llama-arch.o \
+	$(DIR_LLAMA)/llama-batch.o \
+	$(DIR_LLAMA)/llama-chat.o \
+	$(DIR_LLAMA)/llama-context.o \
+	$(DIR_LLAMA)/llama-graph.o \
+	$(DIR_LLAMA)/llama-hparams.o \
+	$(DIR_LLAMA)/llama-impl.o \
+	$(DIR_LLAMA)/llama-io.o \
+	$(DIR_LLAMA)/llama-kv-cache.o \
+	$(DIR_LLAMA)/llama-mmap.o \
+	$(DIR_LLAMA)/llama-model.o \
+	$(DIR_LLAMA)/llama-model-loader.o \
+	$(DIR_LLAMA)/llama-quant.o \
 	$(DIR_LLAMA)/unicode.o \
 	$(DIR_LLAMA)/unicode-data.o
 
+#	$(DIR_LLAMA)/llama-context.o \
+
 OBJ_COMMON = \
 	$(DIR_COMMON)/common.o \
 	$(DIR_COMMON)/arg.o \
@@ -1049,8 +1111,10 @@ $(info I CFLAGS:    $(CFLAGS))
 $(info I CXXFLAGS:  $(CXXFLAGS))
 $(info I NVCCFLAGS: $(NVCCFLAGS))
 $(info I LDFLAGS:   $(LDFLAGS))
+ifneq ($(UNAME_S),cosmocc)
 $(info I CC:        $(shell $(CC)   --version | head -n 1))
 $(info I CXX:       $(shell $(CXX)  --version | head -n 1))
+endif
 ifdef GGML_CUDA
 $(info I NVCC:      $(shell $(NVCC) --version | tail -n 1))
 CUDA_VERSION := $(shell $(NVCC) --version | grep -oP 'release (\K[0-9]+\.[0-9])')
@@ -1196,7 +1260,14 @@ llama-infill: examples/infill/infill.cpp \
 	$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
-llama-run: examples/run/run.cpp \
+llama-run: \
+	examples/run/run.cpp \
+	examples/run/linenoise.cpp/linenoise.cpp \
+	$(OBJ_ALL)
+	$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
+
+llama-run-orig: examples/run/run.cpp \
 	$(OBJ_ALL)
 	$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
@@ -1370,6 +1441,20 @@ rpc-server: examples/rpc/rpc-server.cpp \
 endif # GGML_RPC
 
 llama-server: \
+	examples/server/server.cpp \
+	examples/server/httplib.h \
+	common/chat.h \
+	common/minja/chat-template.hpp \
+	common/json.hpp \
+	common//minja/minja.hpp \
+	$(OBJ_ALL)
+	cmake -DINPUT=examples/server/public/index.html.gz -DOUTPUT=examples/server/index.html.gz.hpp -P scripts/xxd.cmake
+	cmake -DINPUT=examples/server/public_legacy/index.html -DOUTPUT=examples/server/index.html.hpp -P scripts/xxd.cmake
+	cmake -DINPUT=examples/server/public_legacy/loading.html -DOUTPUT=examples/server/loading.html.hpp -P scripts/xxd.cmake
+	$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h %.hpp $<,$^) -Iexamples/server $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS) $(LWINSOCK2)
+
+llama-server-orig: \
 	examples/server/server.cpp \
 	examples/server/utils.hpp \
 	examples/server/httplib.h \