chore(llama.cpp): bump to 'd12cc3d1ca6bba741cd77887ac9c9ee18c8415c7' (#9282)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

Author: mudler

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=66c4f9ded01b29d9120255be1ed8d5835bcbb51d
+LLAMA_VERSION?=d12cc3d1ca6bba741cd77887ac9c9ee18c8415c7
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

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

@@ -1614,6 +1614,7 @@ class BackendServiceImpl final : public backend::Backend::Service {
                         ctx_server.impl->vocab,
                         params_base,
                         ctx_server.get_meta().slot_n_ctx,
+                        ctx_server.get_meta().logit_bias_eog,
                         data);
                 task.id_slot = json_value(data, "id_slot", -1);
 
@@ -2382,6 +2383,7 @@ class BackendServiceImpl final : public backend::Backend::Service {
                         ctx_server.impl->vocab,
                         params_base,
                         ctx_server.get_meta().slot_n_ctx,
+                        ctx_server.get_meta().logit_bias_eog,
                         data);
                 task.id_slot = json_value(data, "id_slot", -1);