Merge branch 'master' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	tests/test-tokenizer-0.cpp

examples/quantize/quantize.cpp

@@ -178,7 +178,7 @@ int main(int argc, char ** argv) {
         usage(argv[0]);
     }
 
-    llama_init_backend(false);
+    llama_backend_init(false);
 
     // parse command line arguments
     const std::string fname_inp = argv[arg_idx];
@@ -253,5 +253,7 @@ int main(int argc, char ** argv) {
         printf("%s:    total time = %8.2f ms\n", __func__, (t_main_end_us - t_main_start_us)/1000.0);
     }
 
+    llama_backend_free();
+
     return 0;
 }