diff --git a/CMakeLists.txt b/CMakeLists.txt
index caea48c50..310a3dcfd 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -225,7 +225,7 @@ foreach(FILE_PATH ${EXTRA_LICENSES})
 endforeach()
 
 if (LLAMA_BUILD_COMMON)
-    license_generate(common)
+    license_generate(llama-common)
 endif()
 
 #
@@ -249,6 +249,10 @@ set_target_properties(llama
 
 install(TARGETS llama LIBRARY PUBLIC_HEADER)
 
+if (LLAMA_BUILD_COMMON)
+    install(TARGETS llama-common LIBRARY)
+endif()
+
 configure_package_config_file(
         ${CMAKE_CURRENT_SOURCE_DIR}/cmake/llama-config.cmake.in
         ${CMAKE_CURRENT_BINARY_DIR}/llama-config.cmake
diff --git a/common/CMakeLists.txt b/common/CMakeLists.txt
index b313a7320..7a911c63e 100644
--- a/common/CMakeLists.txt
+++ b/common/CMakeLists.txt
@@ -1,9 +1,11 @@
-# common
-
 find_package(Threads REQUIRED)
 
 llama_add_compile_flags()
 
+#
+# llama-common-base
+#
+
 # Build info header
 
 if(EXISTS "${PROJECT_SOURCE_DIR}/.git")
@@ -33,17 +35,25 @@ endif()
 
 set(TEMPLATE_FILE "${CMAKE_CURRENT_SOURCE_DIR}/build-info.cpp.in")
 set(OUTPUT_FILE   "${CMAKE_CURRENT_BINARY_DIR}/build-info.cpp")
+
 configure_file(${TEMPLATE_FILE} ${OUTPUT_FILE})
 
-set(TARGET build_info)
-add_library(${TARGET} OBJECT ${OUTPUT_FILE})
+set(TARGET llama-common-base)
+add_library(${TARGET} STATIC ${OUTPUT_FILE})
+
+target_include_directories(${TARGET} PUBLIC .)
+
 if (BUILD_SHARED_LIBS)
     set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON)
 endif()
 
-set(TARGET common)
+#
+# llama-common
+#
 
-add_library(${TARGET} STATIC
+set(TARGET llama-common)
+
+add_library(${TARGET}
     arg.cpp
     arg.h
     base64.hpp
@@ -106,17 +116,24 @@ add_library(${TARGET} STATIC
     jinja/caps.h
     )
 
+set_target_properties(${TARGET} PROPERTIES
+    VERSION ${LLAMA_INSTALL_VERSION}
+    SOVERSION 0
+    MACHO_CURRENT_VERSION 0 # keep macOS linker from seeing oversized version number
+)
+
 target_include_directories(${TARGET} PUBLIC . ../vendor)
 target_compile_features   (${TARGET} PUBLIC cxx_std_17)
 
 if (BUILD_SHARED_LIBS)
     set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON)
+
+    # TODO: make fine-grained exports in the future
+    set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON)
 endif()
 
-target_link_libraries(${TARGET} PRIVATE
-    build_info
-    cpp-httplib
-)
+target_link_libraries(${TARGET} PUBLIC  llama-common-base)
+target_link_libraries(${TARGET} PRIVATE cpp-httplib)
 
 if (LLAMA_LLGUIDANCE)
     include(ExternalProject)
diff --git a/common/arg.cpp b/common/arg.cpp
index 3d0183ed7..6f22f7819 100644
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -1,5 +1,6 @@
 #include "arg.h"
 
+#include "build-info.h"
 #include "chat.h"
 #include "common.h"
 #include "download.h"
@@ -1044,8 +1045,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         {"--version"},
         "show version and build info",
         [](common_params &) {
-            fprintf(stderr, "version: %d (%s)\n", LLAMA_BUILD_NUMBER, LLAMA_COMMIT);
-            fprintf(stderr, "built with %s for %s\n", LLAMA_COMPILER, LLAMA_BUILD_TARGET);
+            fprintf(stderr, "version: %d (%s)\n", llama_build_number(), llama_commit());
+            fprintf(stderr, "built with %s for %s\n", llama_compiler(), llama_build_target());
             exit(0);
         }
     ));
diff --git a/common/build-info.cpp.in b/common/build-info.cpp.in
index aee9d7eaf..f888fd079 100644
--- a/common/build-info.cpp.in
+++ b/common/build-info.cpp.in
@@ -1,4 +1,35 @@
+#include "build-info.h"
+
+#include <cstdio>
+#include <string>
+
 int LLAMA_BUILD_NUMBER = @LLAMA_BUILD_NUMBER@;
-char const *LLAMA_COMMIT = "@LLAMA_BUILD_COMMIT@";
-char const *LLAMA_COMPILER = "@BUILD_COMPILER@";
-char const *LLAMA_BUILD_TARGET = "@BUILD_TARGET@";
+char const * LLAMA_COMMIT = "@LLAMA_BUILD_COMMIT@";
+char const * LLAMA_COMPILER = "@BUILD_COMPILER@";
+char const * LLAMA_BUILD_TARGET = "@BUILD_TARGET@";
+
+int llama_build_number(void) {
+    return LLAMA_BUILD_NUMBER;
+}
+
+const char * llama_commit(void) {
+    return LLAMA_COMMIT;
+}
+
+const char * llama_compiler(void) {
+    return LLAMA_COMPILER;
+}
+
+const char * llama_build_target(void) {
+    return LLAMA_BUILD_TARGET;
+}
+
+const char * llama_build_info(void) {
+    static std::string s = "b" + std::to_string(LLAMA_BUILD_NUMBER) + "-" + LLAMA_COMMIT;
+    return s.c_str();
+}
+
+void llama_print_build_info(void) {
+    fprintf(stderr, "%s: build = %d (%s)\n",      __func__, llama_build_number(), llama_commit());
+    fprintf(stderr, "%s: built with %s for %s\n", __func__, llama_compiler(), llama_build_target());
+}
diff --git a/common/build-info.h b/common/build-info.h
new file mode 100644
index 000000000..382cfa785
--- /dev/null
+++ b/common/build-info.h
@@ -0,0 +1,11 @@
+#pragma once
+
+int llama_build_number(void);
+
+const char * llama_commit(void);
+const char * llama_compiler(void);
+
+const char * llama_build_target(void);
+const char * llama_build_info(void);
+
+void llama_print_build_info(void);
diff --git a/common/common.cpp b/common/common.cpp
index 16f78debd..d3f1cee39 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -1,6 +1,7 @@
 #include "ggml.h"
 #include "gguf.h"
 
+#include "build-info.h"
 #include "common.h"
 #include "log.h"
 #include "llama.h"
@@ -372,7 +373,7 @@ void common_init() {
     const char * build_type = " (debug)";
 #endif
 
-    LOG_DBG("build: %d (%s) with %s for %s%s\n", LLAMA_BUILD_NUMBER, LLAMA_COMMIT, LLAMA_COMPILER, LLAMA_BUILD_TARGET, build_type);
+    LOG_DBG("build: %d (%s) with %s for %s%s\n", llama_build_number(), llama_commit(), llama_compiler(), llama_build_target(), build_type);
 }
 
 std::string common_params_get_system_info(const common_params & params) {
diff --git a/common/common.h b/common/common.h
index 020b6a721..81c269556 100644
--- a/common/common.h
+++ b/common/common.h
@@ -2,9 +2,10 @@
 
 #pragma once
 
+#include "llama-cpp.h"
+
 #include "ggml-opt.h"
 #include "ggml.h"
-#include "llama-cpp.h"
 
 #include <set>
 #include <sstream>
@@ -27,11 +28,6 @@
 #define die(msg)          do { fputs("error: " msg "\n", stderr);                exit(1); } while (0)
 #define die_fmt(fmt, ...) do { fprintf(stderr, "error: " fmt "\n", __VA_ARGS__); exit(1); } while (0)
 
-#define print_build_info() do {                                                                     \
-    fprintf(stderr, "%s: build = %d (%s)\n",      __func__, LLAMA_BUILD_NUMBER, LLAMA_COMMIT);      \
-    fprintf(stderr, "%s: built with %s for %s\n", __func__, LLAMA_COMPILER, LLAMA_BUILD_TARGET);    \
-} while(0)
-
 struct common_time_meas {
     common_time_meas(int64_t & t_acc, bool disable = false);
     ~common_time_meas();
@@ -53,14 +49,6 @@ struct common_adapter_lora_info {
 
 using llama_tokens = std::vector<llama_token>;
 
-// build info
-extern int LLAMA_BUILD_NUMBER;
-extern const char * LLAMA_COMMIT;
-extern const char * LLAMA_COMPILER;
-extern const char * LLAMA_BUILD_TARGET;
-
-const static std::string build_info("b" + std::to_string(LLAMA_BUILD_NUMBER) + "-" + LLAMA_COMMIT);
-
 struct common_control_vector_load_info;
 
 //
diff --git a/common/download.cpp b/common/download.cpp
index 0e0034e1d..c4bb02d90 100644
--- a/common/download.cpp
+++ b/common/download.cpp
@@ -1,5 +1,6 @@
 #include "arg.h"
 
+#include "build-info.h"
 #include "common.h"
 #include "log.h"
 #include "download.h"
@@ -303,7 +304,7 @@ static int common_download_file_single_online(const std::string & url,
         headers.emplace(h.first, h.second);
     }
     if (headers.find("User-Agent") == headers.end()) {
-        headers.emplace("User-Agent", "llama-cpp/" + build_info);
+        headers.emplace("User-Agent", "llama-cpp/" + std::string(llama_build_info()));
     }
     if (!opts.bearer_token.empty()) {
         headers.emplace("Authorization", "Bearer " + opts.bearer_token);
@@ -441,7 +442,7 @@ std::pair<long, std::vector<char>> common_remote_get_content(const std::string
         headers.emplace(h.first, h.second);
     }
     if (headers.find("User-Agent") == headers.end()) {
-        headers.emplace("User-Agent", "llama-cpp/" + build_info);
+        headers.emplace("User-Agent", "llama-cpp/" + std::string(llama_build_info()));
     }
 
     if (params.timeout > 0) {
diff --git a/common/hf-cache.cpp b/common/hf-cache.cpp
index 665c9ff06..38a4c17a9 100644
--- a/common/hf-cache.cpp
+++ b/common/hf-cache.cpp
@@ -1,5 +1,6 @@
 #include "hf-cache.h"
 
+#include "build-info.h"
 #include "common.h"
 #include "log.h"
 #include "http.h"
@@ -200,7 +201,7 @@ static nl::json api_get(const std::string & url,
     auto [cli, parts] = common_http_client(url);
 
     httplib::Headers headers = {
-        {"User-Agent", "llama-cpp/" + build_info},
+        {"User-Agent", "llama-cpp/" + std::string(llama_build_info())},
         {"Accept", "application/json"}
     };
 
diff --git a/common/log.cpp b/common/log.cpp
index b17d2b62c..dec4ef5fc 100644
--- a/common/log.cpp
+++ b/common/log.cpp
@@ -23,6 +23,10 @@
 
 int common_log_verbosity_thold = LOG_DEFAULT_LLAMA;
 
+int common_log_get_verbosity_thold(void) {
+    return common_log_verbosity_thold;
+}
+
 void common_log_set_verbosity_thold(int verbosity) {
     common_log_verbosity_thold = verbosity;
 }
diff --git a/common/log.h b/common/log.h
index f0f8471b5..cf32ca185 100644
--- a/common/log.h
+++ b/common/log.h
@@ -38,7 +38,7 @@ enum log_colors {
 
 // needed by the LOG_TMPL macro to avoid computing log arguments if the verbosity lower
 // set via common_log_set_verbosity()
-extern int common_log_verbosity_thold;
+int  common_log_get_verbosity_thold(void);
 
 void common_log_set_verbosity_thold(int verbosity); // not thread-safe
 
@@ -98,7 +98,7 @@ void common_log_flush         (struct common_log * log);                    // f
 
 #define LOG_TMPL(level, verbosity, ...) \
     do { \
-        if ((verbosity) <= common_log_verbosity_thold) { \
+        if ((verbosity) <= common_log_get_verbosity_thold()) { \
             common_log_add(common_log_main(), (level), __VA_ARGS__); \
         } \
     } while (0)
diff --git a/examples/batched/CMakeLists.txt b/examples/batched/CMakeLists.txt
index 0d439f498..1d7c2a0f6 100644
--- a/examples/batched/CMakeLists.txt
+++ b/examples/batched/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-batched)
 add_executable(${TARGET} batched.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/convert-llama2c-to-ggml/CMakeLists.txt b/examples/convert-llama2c-to-ggml/CMakeLists.txt
index 44e5f722a..2162da4fd 100644
--- a/examples/convert-llama2c-to-ggml/CMakeLists.txt
+++ b/examples/convert-llama2c-to-ggml/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-convert-llama2c-to-ggml)
 add_executable(${TARGET} convert-llama2c-to-ggml.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/debug/CMakeLists.txt b/examples/debug/CMakeLists.txt
index 34593072b..fb1c7e258 100644
--- a/examples/debug/CMakeLists.txt
+++ b/examples/debug/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-debug)
 add_executable(${TARGET} debug.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/diffusion/CMakeLists.txt b/examples/diffusion/CMakeLists.txt
index 396549c80..70228d407 100644
--- a/examples/diffusion/CMakeLists.txt
+++ b/examples/diffusion/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-diffusion-cli)
 add_executable(${TARGET} diffusion-cli.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE llama common ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama llama-common ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/embedding/CMakeLists.txt b/examples/embedding/CMakeLists.txt
index 809040307..0634c7bd8 100644
--- a/examples/embedding/CMakeLists.txt
+++ b/examples/embedding/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-embedding)
 add_executable(${TARGET} embedding.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/eval-callback/CMakeLists.txt b/examples/eval-callback/CMakeLists.txt
index 6439690a5..63fbe59dc 100644
--- a/examples/eval-callback/CMakeLists.txt
+++ b/examples/eval-callback/CMakeLists.txt
@@ -1,7 +1,7 @@
 set(TARGET llama-eval-callback)
 add_executable(${TARGET} eval-callback.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_BUILD_TESTS)
diff --git a/examples/gen-docs/CMakeLists.txt b/examples/gen-docs/CMakeLists.txt
index 25de0af35..aa68cbd78 100644
--- a/examples/gen-docs/CMakeLists.txt
+++ b/examples/gen-docs/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-gen-docs)
 add_executable(${TARGET} gen-docs.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/idle/CMakeLists.txt b/examples/idle/CMakeLists.txt
index d5018fec4..c0fedbbff 100644
--- a/examples/idle/CMakeLists.txt
+++ b/examples/idle/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-idle)
 add_executable(${TARGET} idle.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE llama common ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama llama-common ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)
diff --git a/examples/lookahead/CMakeLists.txt b/examples/lookahead/CMakeLists.txt
index 346861314..5d6e604fa 100644
--- a/examples/lookahead/CMakeLists.txt
+++ b/examples/lookahead/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-lookahead)
 add_executable(${TARGET} lookahead.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/lookup/CMakeLists.txt b/examples/lookup/CMakeLists.txt
index fba78ceda..09f7d2e3c 100644
--- a/examples/lookup/CMakeLists.txt
+++ b/examples/lookup/CMakeLists.txt
@@ -1,23 +1,23 @@
 set(TARGET llama-lookup)
 add_executable(${TARGET} lookup.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 set(TARGET llama-lookup-create)
 add_executable(${TARGET} lookup-create.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 set(TARGET llama-lookup-merge)
 add_executable(${TARGET} lookup-merge.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 set(TARGET llama-lookup-stats)
 add_executable(${TARGET} lookup-stats.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/parallel/CMakeLists.txt b/examples/parallel/CMakeLists.txt
index 847e916de..4fb7a96aa 100644
--- a/examples/parallel/CMakeLists.txt
+++ b/examples/parallel/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-parallel)
 add_executable(${TARGET} parallel.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/passkey/CMakeLists.txt b/examples/passkey/CMakeLists.txt
index 9bc5110c2..12558cc25 100644
--- a/examples/passkey/CMakeLists.txt
+++ b/examples/passkey/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-passkey)
 add_executable(${TARGET} passkey.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/retrieval/CMakeLists.txt b/examples/retrieval/CMakeLists.txt
index 512a602ec..5927ff8a8 100644
--- a/examples/retrieval/CMakeLists.txt
+++ b/examples/retrieval/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-retrieval)
 add_executable(${TARGET} retrieval.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/save-load-state/CMakeLists.txt b/examples/save-load-state/CMakeLists.txt
index 0f50e50de..78024672e 100644
--- a/examples/save-load-state/CMakeLists.txt
+++ b/examples/save-load-state/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-save-load-state)
 add_executable(${TARGET} save-load-state.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/speculative-simple/CMakeLists.txt b/examples/speculative-simple/CMakeLists.txt
index aeaea74fc..5ef3b4131 100644
--- a/examples/speculative-simple/CMakeLists.txt
+++ b/examples/speculative-simple/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-speculative-simple)
 add_executable(${TARGET} speculative-simple.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/speculative/CMakeLists.txt b/examples/speculative/CMakeLists.txt
index c84196bd9..b4e20c717 100644
--- a/examples/speculative/CMakeLists.txt
+++ b/examples/speculative/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-speculative)
 add_executable(${TARGET} speculative.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/sycl/CMakeLists.txt b/examples/sycl/CMakeLists.txt
index e4d5083e6..40e44eefc 100644
--- a/examples/sycl/CMakeLists.txt
+++ b/examples/sycl/CMakeLists.txt
@@ -5,5 +5,5 @@
 set(TARGET llama-ls-sycl-device)
 add_executable(${TARGET} ls-sycl-device.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/examples/training/CMakeLists.txt b/examples/training/CMakeLists.txt
index 64afe6ddc..8bb20d0f2 100644
--- a/examples/training/CMakeLists.txt
+++ b/examples/training/CMakeLists.txt
@@ -1,5 +1,5 @@
 set(TARGET llama-finetune)
 add_executable(${TARGET} finetune.cpp)
 install(TARGETS ${TARGET} RUNTIME)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_11)
diff --git a/pocs/vdot/CMakeLists.txt b/pocs/vdot/CMakeLists.txt
index 6235aec1f..f3776268a 100644
--- a/pocs/vdot/CMakeLists.txt
+++ b/pocs/vdot/CMakeLists.txt
@@ -1,9 +1,9 @@
 set(TARGET llama-vdot)
 add_executable(${TARGET} vdot.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 set(TARGET llama-q8dot)
 add_executable(${TARGET} q8dot.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt
index cd4bc5ef1..b282c3239 100644
--- a/tests/CMakeLists.txt
+++ b/tests/CMakeLists.txt
@@ -10,7 +10,7 @@ function(llama_build source)
     endif()
 
     add_executable(${TEST_TARGET} ${TEST_SOURCES})
-    target_link_libraries(${TEST_TARGET} PRIVATE common)
+    target_link_libraries(${TEST_TARGET} PRIVATE llama llama-common)
     if (LLAMA_TESTS_INSTALL)
         install(TARGETS ${TEST_TARGET} RUNTIME)
     endif()
@@ -105,7 +105,7 @@ function(llama_build_and_test source)
     if (LLAMA_TESTS_INSTALL)
         install(TARGETS ${TEST_TARGET} RUNTIME)
     endif()
-    target_link_libraries(${TEST_TARGET} PRIVATE common)
+    target_link_libraries(${TEST_TARGET} PRIVATE llama-common)
 
     add_test(
         NAME ${TEST_TARGET}
@@ -269,11 +269,11 @@ if (TARGET cpp-httplib)
     get_target_property(_cpp_httplib_defs cpp-httplib INTERFACE_COMPILE_DEFINITIONS)
     if (_cpp_httplib_defs MATCHES "CPPHTTPLIB_OPENSSL_SUPPORT")
         add_library(gguf-model-data STATIC gguf-model-data.cpp)
-        target_link_libraries(gguf-model-data PRIVATE common cpp-httplib)
+        target_link_libraries(gguf-model-data PRIVATE llama-common cpp-httplib)
         target_include_directories(gguf-model-data PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
 
         add_executable(test-gguf-model-data test-gguf-model-data.cpp)
-        target_link_libraries(test-gguf-model-data PRIVATE gguf-model-data common)
+        target_link_libraries(test-gguf-model-data PRIVATE gguf-model-data llama-common)
         llama_test(test-gguf-model-data LABEL "model")
 
         # test-quant-type-selection requires gguf-model-data for remote model metadata
diff --git a/tests/test-quantize-stats.cpp b/tests/test-quantize-stats.cpp
index de587d456..e53a7b355 100644
--- a/tests/test-quantize-stats.cpp
+++ b/tests/test-quantize-stats.cpp
@@ -1,10 +1,13 @@
-#include "ggml.h"
-#include "ggml-cpu.h"
 #include "llama.h"
+
+#include "build-info.h"
 #include "common.h"
 
 #include "../src/llama-model.h"
 
+#include "ggml.h"
+#include "ggml-cpu.h"
+
 #include <algorithm>
 #include <cassert>
 #include <cinttypes>
@@ -298,7 +301,7 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
-    print_build_info();
+    llama_print_build_info();
 
     // load the model
     fprintf(stderr, "Loading model\n");
diff --git a/tools/batched-bench/CMakeLists.txt b/tools/batched-bench/CMakeLists.txt
index 4a46b57a5..f9ffd2d4c 100644
--- a/tools/batched-bench/CMakeLists.txt
+++ b/tools/batched-bench/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-batched-bench)
 add_executable(${TARGET} batched-bench.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/cli/CMakeLists.txt b/tools/cli/CMakeLists.txt
index b08fff4c2..7e01abb81 100644
--- a/tools/cli/CMakeLists.txt
+++ b/tools/cli/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-cli)
 add_executable(${TARGET} cli.cpp)
-target_link_libraries(${TARGET} PRIVATE server-context PUBLIC common ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE server-context PUBLIC llama-common ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 include_directories(../server)
diff --git a/tools/completion/CMakeLists.txt b/tools/completion/CMakeLists.txt
index 126ae6ab3..2c7df8065 100644
--- a/tools/completion/CMakeLists.txt
+++ b/tools/completion/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-completion)
 add_executable(${TARGET} completion.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/cvector-generator/CMakeLists.txt b/tools/cvector-generator/CMakeLists.txt
index baeb4d00c..c0f2c2407 100644
--- a/tools/cvector-generator/CMakeLists.txt
+++ b/tools/cvector-generator/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-cvector-generator)
 add_executable(${TARGET} cvector-generator.cpp pca.hpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/cvector-generator/cvector-generator.cpp b/tools/cvector-generator/cvector-generator.cpp
index fd6e5ddd2..8c6b3d868 100644
--- a/tools/cvector-generator/cvector-generator.cpp
+++ b/tools/cvector-generator/cvector-generator.cpp
@@ -2,6 +2,7 @@
 #include "gguf.h"
 
 #include "arg.h"
+#include "build-info.h"
 #include "common.h"
 #include "llama.h"
 #include "pca.hpp"
@@ -420,7 +421,7 @@ int main(int argc, char ** argv) {
     params.cb_eval_user_data = &cb_data;
     params.warmup = false;
 
-    print_build_info();
+    llama_print_build_info();
     llama_backend_init();
     llama_numa_init(params.numa);
 
diff --git a/tools/export-lora/CMakeLists.txt b/tools/export-lora/CMakeLists.txt
index cddfa77f0..b122a8752 100644
--- a/tools/export-lora/CMakeLists.txt
+++ b/tools/export-lora/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-export-lora)
 add_executable(${TARGET} export-lora.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/fit-params/CMakeLists.txt b/tools/fit-params/CMakeLists.txt
index 34c3373f8..25c409663 100644
--- a/tools/fit-params/CMakeLists.txt
+++ b/tools/fit-params/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-fit-params)
 add_executable(${TARGET} fit-params.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/gguf-split/CMakeLists.txt b/tools/gguf-split/CMakeLists.txt
index 9b2125087..b40e07ab5 100644
--- a/tools/gguf-split/CMakeLists.txt
+++ b/tools/gguf-split/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-gguf-split)
 add_executable(${TARGET} gguf-split.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/gguf-split/gguf-split.cpp b/tools/gguf-split/gguf-split.cpp
index f99f0299b..8a6b5c198 100644
--- a/tools/gguf-split/gguf-split.cpp
+++ b/tools/gguf-split/gguf-split.cpp
@@ -1,7 +1,10 @@
+#include "llama.h"
+
+#include "build-info.h"
+#include "common.h"
+
 #include "ggml.h"
 #include "gguf.h"
-#include "llama.h"
-#include "common.h"
 
 #include <algorithm>
 #include <cinttypes>
@@ -101,8 +104,8 @@ static void split_params_parse_ex(int argc, const char ** argv, split_params & p
             split_print_usage(argv[0]);
             exit(0);
         } else if (arg == "--version") {
-            fprintf(stderr, "version: %d (%s)\n", LLAMA_BUILD_NUMBER, LLAMA_COMMIT);
-            fprintf(stderr, "built with %s for %s\n", LLAMA_COMPILER, LLAMA_BUILD_TARGET);
+            fprintf(stderr, "version: %d (%s)\n", llama_build_number(), llama_commit());
+            fprintf(stderr, "built with %s for %s\n", llama_compiler(), llama_build_target());
             exit(0);
         } else if (arg == "--dry-run") {
             arg_found = true;
diff --git a/tools/imatrix/CMakeLists.txt b/tools/imatrix/CMakeLists.txt
index 5af6263f9..361c4577d 100644
--- a/tools/imatrix/CMakeLists.txt
+++ b/tools/imatrix/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-imatrix)
 add_executable(${TARGET} imatrix.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/llama-bench/CMakeLists.txt b/tools/llama-bench/CMakeLists.txt
index b8543a969..93d6a3aa2 100644
--- a/tools/llama-bench/CMakeLists.txt
+++ b/tools/llama-bench/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-bench)
 add_executable(${TARGET} llama-bench.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/llama-bench/llama-bench.cpp b/tools/llama-bench/llama-bench.cpp
index b15a26a98..59920ab51 100644
--- a/tools/llama-bench/llama-bench.cpp
+++ b/tools/llama-bench/llama-bench.cpp
@@ -19,6 +19,7 @@
 #include <vector>
 #include <unordered_set>
 
+#include "build-info.h"
 #include "common.h"
 #include "download.h"
 #include "ggml.h"
@@ -1624,8 +1625,8 @@ struct test {
     }
 };
 
-const std::string test::build_commit = LLAMA_COMMIT;
-const int         test::build_number = LLAMA_BUILD_NUMBER;
+const std::string test::build_commit = llama_commit();
+const int         test::build_number = llama_build_number();
 
 struct printer {
     virtual ~printer() {}
diff --git a/tools/mtmd/CMakeLists.txt b/tools/mtmd/CMakeLists.txt
index 3bafde178..e5ad9b81b 100644
--- a/tools/mtmd/CMakeLists.txt
+++ b/tools/mtmd/CMakeLists.txt
@@ -86,12 +86,12 @@ if (TARGET BUILD_INFO)
     add_dependencies(mtmd-helper BUILD_INFO)
 endif()
 
-# if mtmd is linked against common, we throw an error
+# if mtmd is linked against llama-common, we throw an error
 if (TARGET mtmd)
     get_target_property(libs mtmd LINK_LIBRARIES)
-    if (libs AND "common" IN_LIST libs)
+    if (libs AND "llama-common" IN_LIST libs)
         message(FATAL_ERROR "mtmd is designed to be a public library.\n"
-                            "It must not link against common")
+                            "It must not link against llama-common")
     endif()
 endif()
 
@@ -106,11 +106,11 @@ set_target_properties  (${TARGET} PROPERTIES OUTPUT_NAME llama-mtmd-cli)
 if(LLAMA_TOOLS_INSTALL)
     install(TARGETS ${TARGET} RUNTIME)
 endif()
-target_link_libraries  (${TARGET} PRIVATE common mtmd Threads::Threads)
+target_link_libraries  (${TARGET} PRIVATE llama-common mtmd Threads::Threads)
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 # mtmd-debug tool
 add_executable(llama-mtmd-debug debug/mtmd-debug.cpp)
 set_target_properties(llama-mtmd-debug PROPERTIES OUTPUT_NAME llama-mtmd-debug)
-target_link_libraries(llama-mtmd-debug PRIVATE common mtmd Threads::Threads)
+target_link_libraries(llama-mtmd-debug PRIVATE llama-common mtmd Threads::Threads)
 target_compile_features(llama-mtmd-debug PRIVATE cxx_std_17)
diff --git a/tools/parser/CMakeLists.txt b/tools/parser/CMakeLists.txt
index 55e0c6343..a8df0e7e6 100644
--- a/tools/parser/CMakeLists.txt
+++ b/tools/parser/CMakeLists.txt
@@ -2,7 +2,7 @@ if (NOT WIN32 OR NOT BUILD_SHARED_LIBS)
     # this tool is disabled on Windows when building with shared libraries because it uses internal functions not exported with LLAMA_API
     set(TARGET llama-debug-template-parser)
     add_executable(${TARGET} debug-template-parser.cpp)
-    target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+    target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
     target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
     if(LLAMA_TOOLS_INSTALL)
@@ -12,7 +12,7 @@ endif()
 
 set(TARGET llama-template-analysis)
 add_executable(${TARGET} template-analysis.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/perplexity/CMakeLists.txt b/tools/perplexity/CMakeLists.txt
index 12b28b2be..0c194ee7f 100644
--- a/tools/perplexity/CMakeLists.txt
+++ b/tools/perplexity/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-perplexity)
 add_executable(${TARGET} perplexity.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/quantize/CMakeLists.txt b/tools/quantize/CMakeLists.txt
index bd9ddbd67..965adc005 100644
--- a/tools/quantize/CMakeLists.txt
+++ b/tools/quantize/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-quantize)
 add_executable(${TARGET} quantize.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_include_directories(${TARGET} PRIVATE ../../common)
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
diff --git a/tools/quantize/quantize.cpp b/tools/quantize/quantize.cpp
index a882c78f1..3d33d47d9 100644
--- a/tools/quantize/quantize.cpp
+++ b/tools/quantize/quantize.cpp
@@ -1,5 +1,8 @@
-#include "common.h"
 #include "llama.h"
+
+#include "build-info.h"
+#include "common.h"
+
 #include "gguf.h"
 
 #include <algorithm>
@@ -709,7 +712,7 @@ int main(int argc, char ** argv) {
         }
     }
 
-    print_build_info();
+    llama_print_build_info();
 
     if (params.dry_run) {
         fprintf(stderr, "%s: calculating quantization size for '%s' as %s", __func__, fname_inp.c_str(), ftype_str.c_str());
diff --git a/tools/results/CMakeLists.txt b/tools/results/CMakeLists.txt
index 2843b8488..643eb0292 100644
--- a/tools/results/CMakeLists.txt
+++ b/tools/results/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-results)
 add_executable(${TARGET} results.cpp)
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/tools/server/CMakeLists.txt b/tools/server/CMakeLists.txt
index 451a045fe..0cce99f59 100644
--- a/tools/server/CMakeLists.txt
+++ b/tools/server/CMakeLists.txt
@@ -23,7 +23,7 @@ endif()
 
 target_include_directories(${TARGET} PRIVATE ../mtmd)
 target_include_directories(${TARGET} PRIVATE ${CMAKE_SOURCE_DIR})
-target_link_libraries(${TARGET} PUBLIC common mtmd ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PUBLIC llama-common mtmd ${CMAKE_THREAD_LIBS_INIT})
 
 
 # llama-server executable
@@ -68,6 +68,6 @@ install(TARGETS ${TARGET} RUNTIME)
 
 target_include_directories(${TARGET} PRIVATE ../mtmd)
 target_include_directories(${TARGET} PRIVATE ${CMAKE_SOURCE_DIR})
-target_link_libraries(${TARGET} PRIVATE server-context PUBLIC common cpp-httplib ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE server-context PUBLIC llama-common cpp-httplib ${CMAKE_THREAD_LIBS_INIT})
 
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/tools/server/server-context.cpp b/tools/server/server-context.cpp
index 41bdad6f8..4b899ecf0 100644
--- a/tools/server/server-context.cpp
+++ b/tools/server/server-context.cpp
@@ -4,6 +4,7 @@
 #include "server-task.h"
 #include "server-queue.h"
 
+#include "build-info.h"
 #include "common.h"
 #include "llama.h"
 #include "log.h"
@@ -3010,7 +3011,7 @@ server_context_meta server_context::get_meta() const {
     auto eos_token_str = eos_id != LLAMA_TOKEN_NULL ? common_token_to_piece(impl->ctx, eos_id, true) : "";
 
     return server_context_meta {
-        /* build_info             */ build_info,
+        /* build_info             */ std::string(llama_build_info()),
         /* model_name             */ impl->model_name,
         /* model_aliases          */ impl->model_aliases,
         /* model_tags             */ impl->model_tags,
diff --git a/tools/server/server-models.cpp b/tools/server/server-models.cpp
index 5667c98ef..a1eeec30e 100644
--- a/tools/server/server-models.cpp
+++ b/tools/server/server-models.cpp
@@ -1,6 +1,7 @@
 #include "server-common.h"
 #include "server-models.h"
 
+#include "build-info.h"
 #include "preset.h"
 #include "download.h"
 
@@ -936,7 +937,7 @@ void server_models_routes::init_routes() {
                     {"n_ctx",  0},
                 }},
                 {"webui_settings", webui_settings},
-                {"build_info",     build_info},
+                {"build_info",     std::string(llama_build_info())},
             });
             return res;
         }
diff --git a/tools/server/server-task.cpp b/tools/server/server-task.cpp
index 0312f098a..4fb953b49 100644
--- a/tools/server/server-task.cpp
+++ b/tools/server/server-task.cpp
@@ -1,5 +1,6 @@
 #include "server-task.h"
 
+#include "build-info.h"
 #include "chat.h"
 #include "common.h"
 #include "json-schema-to-grammar.h"
@@ -791,7 +792,7 @@ json server_task_result_cmpl_final::to_json_oaicompat() {
         })},
         {"created",            t},
         {"model",              oaicompat_model},
-        {"system_fingerprint", build_info},
+        {"system_fingerprint", std::string(llama_build_info())},
         {"object",             "text_completion"},
         {"usage",              usage_json_oaicompat()},
         {"id", oaicompat_cmpl_id}
@@ -839,7 +840,7 @@ json server_task_result_cmpl_final::to_json_oaicompat_chat() {
         {"choices",            json::array({choice})},
         {"created",            t},
         {"model",              oaicompat_model},
-        {"system_fingerprint", build_info},
+        {"system_fingerprint", std::string(llama_build_info())},
         {"object",             "chat.completion"},
         {"usage",              usage_json_oaicompat()},
         {"id", oaicompat_cmpl_id}
@@ -876,7 +877,7 @@ json server_task_result_cmpl_final::to_json_oaicompat_chat_stream() {
             {"created", t},
             {"id", oaicompat_cmpl_id},
             {"model", oaicompat_model},
-            {"system_fingerprint", build_info},
+            {"system_fingerprint", std::string(llama_build_info())},
             {"object", "chat.completion.chunk"},
         });
     }
@@ -892,7 +893,7 @@ json server_task_result_cmpl_final::to_json_oaicompat_chat_stream() {
         {"created",            t},
         {"id",                 oaicompat_cmpl_id},
         {"model",              oaicompat_model},
-        {"system_fingerprint", build_info},
+        {"system_fingerprint", std::string(llama_build_info())},
         {"object",             "chat.completion.chunk"},
     });
 
@@ -904,7 +905,7 @@ json server_task_result_cmpl_final::to_json_oaicompat_chat_stream() {
             {"created",            t},
             {"id",                 oaicompat_cmpl_id},
             {"model",              oaicompat_model},
-            {"system_fingerprint", build_info},
+            {"system_fingerprint", std::string(llama_build_info())},
             {"object",             "chat.completion.chunk"},
             {"usage",              usage_json_oaicompat()},
         });
@@ -1469,7 +1470,7 @@ json server_task_result_cmpl_partial::to_json_oaicompat() {
         })},
         {"created",            t},
         {"model",              oaicompat_model},
-        {"system_fingerprint", build_info},
+        {"system_fingerprint", std::string(llama_build_info())},
         {"object",             "text_completion"},
         {"id",                 oaicompat_cmpl_id}
     };
@@ -1506,7 +1507,7 @@ json server_task_result_cmpl_partial::to_json_oaicompat_chat() {
             {"created", t},
             {"id", oaicompat_cmpl_id},
             {"model", oaicompat_model},
-            {"system_fingerprint", build_info},
+            {"system_fingerprint", std::string(llama_build_info())},
             {"object", "chat.completion.chunk"},
         });
     };
diff --git a/tools/server/server.cpp b/tools/server/server.cpp
index fe640b978..06318463f 100644
--- a/tools/server/server.cpp
+++ b/tools/server/server.cpp
@@ -5,6 +5,7 @@
 #include "server-tools.h"
 
 #include "arg.h"
+#include "build-info.h"
 #include "common.h"
 #include "llama.h"
 #include "log.h"
@@ -108,7 +109,7 @@ int main(int argc, char ** argv) {
     llama_backend_init();
     llama_numa_init(params.numa);
 
-    LOG_INF("build_info: %s\n", build_info.c_str());
+    LOG_INF("build_info: %s\n", llama_build_info());
     LOG_INF("%s\n", common_params_get_system_info(params).c_str());
 
     server_http_context ctx_http;
diff --git a/tools/tokenize/CMakeLists.txt b/tools/tokenize/CMakeLists.txt
index feed9a106..1e1836575 100644
--- a/tools/tokenize/CMakeLists.txt
+++ b/tools/tokenize/CMakeLists.txt
@@ -3,5 +3,5 @@ add_executable(${TARGET} tokenize.cpp)
 if(LLAMA_TOOLS_INSTALL)
     install(TARGETS ${TARGET} RUNTIME)
 endif()
-target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
diff --git a/tools/tts/CMakeLists.txt b/tools/tts/CMakeLists.txt
index 76320d4c2..26a8bb8f2 100644
--- a/tools/tts/CMakeLists.txt
+++ b/tools/tts/CMakeLists.txt
@@ -1,6 +1,6 @@
 set(TARGET llama-tts)
 add_executable(${TARGET} tts.cpp)
-target_link_libraries(${TARGET} PRIVATE llama common ${CMAKE_THREAD_LIBS_INIT})
+target_link_libraries(${TARGET} PRIVATE llama llama-common ${CMAKE_THREAD_LIBS_INIT})
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
diff --git a/vendor/cpp-httplib/CMakeLists.txt b/vendor/cpp-httplib/CMakeLists.txt
index 78dc48332..28485a0ce 100644
--- a/vendor/cpp-httplib/CMakeLists.txt
+++ b/vendor/cpp-httplib/CMakeLists.txt
@@ -5,6 +5,8 @@ find_package(Threads REQUIRED)
 
 llama_add_compile_flags()
 
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
 add_library(${TARGET} STATIC httplib.cpp httplib.h)
 
 # disable warnings in 3rd party code