chore(deps): bump llama.cpp to 'df36bce667bf14f8e538645547754386f9516326'

Signed-off-by: Ettore Di Giacinto <[email protected]>

Author: mudler

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=29c8fbe4e05fd23c44950d0958299e25fbeabc5c
+LLAMA_VERSION?=df36bce667bf14f8e538645547754386f9516326
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/grpc-server.cpp

@@ -55,7 +55,7 @@ static void start_llama_server(server_context& ctx_server) {
     // print sample chat example to make it clear which template is used
     LOG_INF("%s: chat template, chat_template: %s, example_format: '%s'\n", __func__,
         common_chat_templates_source(ctx_server.chat_templates.get()),
-        common_chat_format_example(ctx_server.chat_templates.get(), ctx_server.params_base.use_jinja).c_str());
+        common_chat_format_example(ctx_server.chat_templates.get(), ctx_server.params_base.use_jinja).c_str(), params.default_template_kwargs);
 
     // Reset the chat templates
     // TODO: We should make this configurable by respecting the option that is already present in LocalAI for vLLM