Merge master into server-cfg

examples/server/CMakeLists.txt

@@ -2,6 +2,7 @@ set(TARGET server)
 option(LLAMA_SERVER_VERBOSE "Build verbose logging option for Server" ON)
 include_directories(${CMAKE_CURRENT_SOURCE_DIR})
 add_executable(${TARGET} server.cpp json.hpp httplib.h)
+install(TARGETS ${TARGET} RUNTIME)
 target_compile_definitions(${TARGET} PRIVATE
     SERVER_VERBOSE=$<BOOL:${LLAMA_SERVER_VERBOSE}>
 )

examples/server/README.md

@@ -66,6 +66,7 @@ Using [curl](https://curl.se/). On Windows `curl.exe` should be available in the
 ```sh
 curl --request POST \
     --url http://localhost:8080/completion \
+    --header "Content-Type: application/json" \
     --data '{"prompt": "Building a website can be done in 10 simple steps:","n_predict": 128}'
 ```
 

examples/server/chat.sh

@@ -32,6 +32,7 @@ tokenize() {
         --silent \
         --request POST \
         --url "${API_URL}/tokenize" \
+        --header "Content-Type: application/json" \
         --data-raw "$(jq -ns --arg content "$1" '{content:$content}')" \
     | jq '.tokens[]'
 }
@@ -64,6 +65,7 @@ chat_completion() {
         --no-buffer \
         --request POST \
         --url "${API_URL}/completion" \
+        --header "Content-Type: application/json" \
         --data-raw "${DATA}")
 
     printf "\n"

examples/server/server.cpp

@@ -611,6 +611,8 @@ static void server_print_usage(const char * argv0, const gpt_params & params,
     fprintf(stderr, "  -v, --verbose         verbose output (default: %s)\n", server_verbose ? "enabled" : "disabled");
     fprintf(stderr, "  -t N, --threads N     number of threads to use during computation (default: %d)\n", params.n_threads);
     fprintf(stderr, "  -c N, --ctx-size N    size of the prompt context (default: %d)\n", params.n_ctx);
+    fprintf(stderr, "  --rope-freq-base N    RoPE base frequency (default: %.1f)\n", params.rope_freq_base);
+    fprintf(stderr, "  --rope-freq-scale N   RoPE frequency scaling factor (default: %g)\n", params.rope_freq_scale);
     fprintf(stderr, "  -b N, --batch-size N  batch size for prompt processing (default: %d)\n", params.n_batch);
     fprintf(stderr, "  --memory-f32          use f32 instead of f16 for memory key+value (default: disabled)\n");
     fprintf(stderr, "                        not recommended: doubles context memory required and no measurable increase in quality\n");
@@ -698,6 +700,18 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
                 break;
             }
             params.n_ctx = std::stoi(argv[i]);
+        } else if (arg == "--rope-freq-base") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            params.rope_freq_base = std::stof(argv[i]);
+        } else if (arg == "--rope-freq-scale") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            params.rope_freq_scale = std::stof(argv[i]);
         } else if (arg == "--memory-f32" || arg == "--memory_f32") {
             params.memory_f16 = false;
         } else if (arg == "--threads" || arg == "-t") {