swift : Package compile breaks due to ggml-metal.metal (#1831)

* Ignore metal file in spm

* Add ggml.h to spm public Headers

---------

Co-authored-by: Vogel Frederik <vogel.frederik@linecorp.com>

.gitignore

@@ -32,6 +32,7 @@ models/*
 /result
 /perplexity
 /embedding
+/train-text-from-scratch
 /benchmark-matmult
 /vdot
 /Pipfile

Makefile

@@ -1,5 +1,5 @@
 # Define the default target now so that it is always the first target
-BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot
+BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot train-text-from-scratch
 
 ifdef LLAMA_BUILD_SERVER
 	BUILD_TARGETS += server
@@ -259,7 +259,7 @@ libllama.so: llama.o ggml.o $(OBJS)
 	$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
 
 clean:
-	rm -vf *.o main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server vdot build-info.h
+	rm -vf *.o *.so main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server vdot train-text-from-scratch build-info.h
 
 #
 # Examples
@@ -289,6 +289,9 @@ save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.
 server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp build-info.h ggml.o llama.o common.o $(OBJS)
 	$(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS)
 
+train-text-from-scratch: examples/train-text-from-scratch/train-text-from-scratch.cpp    build-info.h ggml.o llama.o $(OBJS)
+	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
+
 build-info.h: $(wildcard .git/index) scripts/build-info.sh
 	@sh scripts/build-info.sh > $@.tmp
 	@if ! cmp -s $@.tmp $@; then \

Package.swift

@@ -11,6 +11,7 @@ let package = Package(
         .target(
             name: "llama",
             path: ".",
+            exclude: ["ggml-metal.metal"],
             sources: ["ggml.c", "llama.cpp"],
             publicHeadersPath: "spm-headers",
             cSettings: [.unsafeFlags(["-Wno-shorten-64-to-32"]), .define("GGML_USE_ACCELERATE")],

examples/server/README.md

@@ -16,6 +16,10 @@ This example allow you to have a llama.cpp http server to interact from a web pa
 To get started right away, run the following command, making sure to use the correct path for the model you have:
 
 #### Unix-based systems (Linux, macOS, etc.):
+Make sure to build with the server option on
+```bash
+LLAMA_BUILD_SERVER=1 make
+```
 
 ```bash
 ./server -m models/7B/ggml-model.bin --ctx_size 2048

spm-headers/ggml.h

@@ -0,0 +1 @@
+../ggml.h