chore(deps): bump llama.cpp to 4ccea213bc629c4eef7b520f7f6c59ce9bbdaca0 (#5143)

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

Author: mudler

Makefile

@@ -6,7 +6,7 @@ BINARY_NAME=local-ai
 DETECT_LIBS?=true
 
 # llama.cpp versions
-CPPLLAMA_VERSION?=916c83bfe7f8b08ada609c3b8e583cf5301e594b
+CPPLLAMA_VERSION?=4ccea213bc629c4eef7b520f7f6c59ce9bbdaca0
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp

backend/cpp/llama/Makefile

@@ -8,7 +8,7 @@ ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
 TARGET?=--target grpc-server
 
 # Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
-CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
+CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF -DLLAMA_CURL=OFF
 
 # If build type is cublas, then we set -DGGML_CUDA=ON to CMAKE_ARGS automatically
 ifeq ($(BUILD_TYPE),cublas)