Include server in releases + other build system cleanups (#1610)

Set `LLAMA_BUILD_SERVER` in workflow so the `server` example gets build. This currently only applies to Windows builds because it seems like only Windows binary artifacts are included in releases.

Add `server` example target to `Makefile` (still uses `LLAMA_BUILD_SERVER` define and does not build by default)

Fix issue where `vdot` binary wasn't removed when running `make clean`.

Fix compile warnings in `server` example.

Add `.hpp` files to trigger workflow (the server example has one).

.github/workflows/build.yml

@@ -10,10 +10,10 @@ on:
   push:
     branches:
       - master
-    paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp']
+    paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp']
   pull_request:
     types: [opened, synchronize, reopened]
-    paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp']
+    paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp']
 
 env:
  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
@@ -157,15 +157,15 @@ jobs:
       matrix:
         include:
           - build: 'avx2'
-            defines: ''
+            defines: '-DLLAMA_BUILD_SERVER=ON'
           - build: 'avx'
-            defines: '-DLLAMA_AVX2=OFF'
+            defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF'
           - build: 'avx512'
-            defines: '-DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
+            defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
           - build: 'clblast'
-            defines: '-DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
+            defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
           - build: 'openblas'
-            defines: '-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
+            defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
 
     steps:
       - name: Clone
@@ -292,7 +292,7 @@ jobs:
         run: |
           mkdir build
           cd build
-          cmake .. -DLLAMA_CUBLAS=ON
+          cmake .. -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON
           cmake --build . --config Release
 
       - name: Get commit hash

Makefile

@@ -1,5 +1,11 @@
 # Define the default target now so that it is always the first target
-default: main quantize quantize-stats perplexity embedding vdot
+BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot
+
+ifdef LLAMA_BUILD_SERVER
+	BUILD_TARGETS += server
+endif
+
+default: $(BUILD_TARGETS)
 
 ifndef UNAME_S
 UNAME_S := $(shell uname -s)
@@ -210,7 +216,7 @@ 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 build-info.h
+	rm -vf *.o main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server vdot build-info.h
 
 #
 # Examples
@@ -237,6 +243,9 @@ 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 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)
+
 build-info.h: $(wildcard .git/index) scripts/build-info.sh
 	@sh scripts/build-info.sh > $@.tmp
 	@if ! cmp -s $@.tmp $@; then \

examples/server/server.cpp

@@ -61,7 +61,7 @@ struct llama_server_context
     std::vector<llama_token> prompt_tokens = ::llama_tokenize(ctx, params.prompt, true);
     // compare the evaluated prompt with the new prompt
     int new_prompt_len = 0;
-    for (int i = 0;i < prompt_tokens.size(); i++) {
+    for (size_t i = 0; i < prompt_tokens.size(); i++) {
       if (i < processed_tokens.size() &&
         processed_tokens[i] == prompt_tokens[i])
       {
@@ -71,7 +71,7 @@ struct llama_server_context
       {
         embd_inp.push_back(prompt_tokens[i]);
         if(new_prompt_len == 0) {
-          if(i - 1 < n_past) {
+          if(int32_t(i) - 1 < n_past) {
             processed_tokens.erase(processed_tokens.begin() + i, processed_tokens.end());
           }
           // Evaluate the new fragment prompt from the last token processed.
@@ -136,7 +136,7 @@ struct llama_server_context
     {
       // out of user input, sample next token
       const float temp = params.temp;
-      const int32_t top_k = params.top_k <= 0 ? llama_n_vocab(ctx) : params.top_k;
+      // const int32_t top_k = params.top_k <= 0 ? llama_n_vocab(ctx) : params.top_k;
       const float top_p = params.top_p;
       const float tfs_z = params.tfs_z;
       const float typical_p = params.typical_p;
@@ -306,12 +306,12 @@ struct llama_server_context
     // Avoid add the no show words to the response
     for (std::vector<llama_token> word_tokens : no_show_words)
     {
-      int match_token = 1;
+      size_t match_token = 1;
       if (tokens_predicted.front() == word_tokens.front())
       {
         bool execute_matching = true;
         if (tokens_predicted.size() > 1) { // if previus tokens had been tested
-          for (int i = 1; i < word_tokens.size(); i++)
+          for (size_t i = 1; i < word_tokens.size(); i++)
           {
             if (i >= tokens_predicted.size()) {
               match_token = i;
@@ -601,7 +601,7 @@ int main(int argc, char **argv)
 
   Server svr;
 
-  svr.Get("/", [](const Request &req, Response &res)
+  svr.Get("/", [](const Request &, Response &res)
           { res.set_content("<h1>llama.cpp server works</h1>", "text/html"); });
 
   svr.Post("/completion", [&llama](const Request &req, Response &res)
@@ -649,7 +649,7 @@ int main(int argc, char **argv)
                       {"tokens_predicted", llama.num_tokens_predicted}};
                   return res.set_content(data.dump(), "application/json");
                 }
-                catch (json::exception e)
+                catch (const json::exception &e)
                 {
                   // Some tokens have bad UTF-8 strings, the json parser is very sensitive
                   json data = {
@@ -701,7 +701,7 @@ int main(int argc, char **argv)
                         {"content", result },
                         {"stop", !llama.has_next_token }};
               return res.set_content(data.dump(), "application/json");
-            } catch (json::exception e) {
+            } catch (const json::exception &e) {
               // Some tokens have bad UTF-8 strings, the json parser is very sensitive
               json data = {
                         {"content", "" },