diff --git a/Makefile b/Makefile
index 920a4e2e..9e3ca433 100644
--- a/Makefile
+++ b/Makefile
@@ -5,7 +5,7 @@ BINARY_NAME=local-ai
 
 # llama.cpp versions
 GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=1ea2a0036e88172d6c8bf7e1a1989a03894dc955
+CPPLLAMA_VERSION?=1e374365d170b7f692fd7753c145e21bc14486c8
 
 # gpt4all version
 GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
diff --git a/backend/cpp/llama/grpc-server.cpp b/backend/cpp/llama/grpc-server.cpp
index fb1e1388..ccf083c2 100644
--- a/backend/cpp/llama/grpc-server.cpp
+++ b/backend/cpp/llama/grpc-server.cpp
@@ -791,7 +791,7 @@ struct llama_server_context
                     sampler_names.emplace_back(sampler_name);
                 }
             }
-            slot->sparams.samplers_sequence = sampler_types_from_names(sampler_names, false);
+            slot->sparams.samplers_sequence = llama_sampling_types_from_names(sampler_names, false);
         }
         else
         {
@@ -1146,7 +1146,7 @@ struct llama_server_context
         std::vector<std::string> samplers_sequence;
         for (const auto &sampler_type : slot.sparams.samplers_sequence)
         {
-            samplers_sequence.emplace_back(sampler_type_to_name_string(sampler_type));
+            samplers_sequence.emplace_back(llama_sampling_type_to_str(sampler_type));
         }
 
         return json {