enable server

Author: SlyEcho

.devops/full.Dockerfile

@@ -14,6 +14,6 @@ WORKDIR /app
 
 COPY . .
 
-RUN make
+RUN make && make server
 
 ENTRYPOINT ["/app/.devops/tools.sh"]

.devops/tools.sh

@@ -16,6 +16,8 @@ elif [[ $arg1 == '--quantize' || $arg1 == '-q' ]]; then
     ./quantize $arg2
 elif [[ $arg1 == '--run' || $arg1 == '-r' ]]; then
     ./main $arg2
+elif [[ $arg1 == '--serve' || $arg1 == '-s' ]]; then
+    ./server $arg2
 elif [[ $arg1 == '--all-in-one' || $arg1 == '-a' ]]; then
     echo "Converting PTH to GGML..."
     for i in `ls $1/$2/ggml-model-f16.bin*`; do
@@ -35,6 +37,8 @@ else
     echo "              ex: \"/models/7B/\" 1"
     echo "  --quantize (-q): Optimize with quantization process ggml"
     echo "              ex: \"/models/7B/ggml-model-f16.bin\" \"/models/7B/ggml-model-q4_0.bin\" 2"
+    echo "  --serve (-s): Run the server"
+    echo "              ex: -m /models/7B/ggml-model-q4_0.bin -host 0.0.0.0 -port 8080"
     echo "  --all-in-one (-a): Execute --convert & --quantize"
     echo "              ex: \"/models/\" 7B"
 fi

.github/workflows/build.yml

@@ -211,7 +211,7 @@ jobs:
         run: |
           mkdir build
           cd build
-          cmake .. ${{ matrix.defines }}
+          cmake .. ${{ matrix.defines }} -DLLAMA_BUILD_SERVER=ON
           cmake --build . --config Release
           cp ../LICENSE ./bin/Release/llama.cpp.txt
 
@@ -292,7 +292,7 @@ jobs:
         run: |
           mkdir build
           cd build
-          cmake .. -DLLAMA_CUBLAS=ON
+          cmake .. -DLLAMA_CUBLAS=ON -DLLAMA_BUILD_SERVER=ON
           cmake --build . --config Release
 
       - name: Get commit hash

Makefile

@@ -237,6 +237,9 @@ embedding: examples/embedding/embedding.cpp build-info.h ggml.o llama.o common.o
 save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.o llama.o common.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 
+server: examples/server/server.cpp build-info.h ggml.o llama.o common.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 \