!1 init llama.cpp package

From: @zhoupengcheng11 
Reviewed-by: @xiezhipeng1 
Signed-off-by: @xiezhipeng1

llama.cpp.spec

@@ -0,0 +1,43 @@
+%define debug_package %{nil}
+%global llama_commitid master-3ebb009
+
+Name:       llama.cpp
+Version:    20230815
+Release:    1
+License:    MIT
+Summary:    Port of English lagre model LLaMA implemented based on C/C++
+
+URL:            https://github.com/ggerganov/llama.cpp
+Source0:        https://github.com/ggerganov/llama.cpp/archive/refs/tags/%{llama_commitid}.tar.gz
+
+BuildRequires:  gcc,gcc-c++,cmake
+
+%description
+Port of English lagre model LLaMA implemented based on C/C++,
+it can be used for model dialogue based on local laptops.
+
+%prep
+%autosetup -b 0 -n %{name}-%{llama_commitid} -p1
+
+%build
+mkdir llama_builddir
+pushd llama_builddir
+cmake ..
+%make_build
+popd
+
+%install
+pushd llama_builddir
+%make_install
+mv %{buildroot}%{_prefix}/local/bin/main  %{buildroot}%{_prefix}/local/bin/llama_cpp_main
+mv %{buildroot}%{_prefix}/local/*  %{buildroot}%{_prefix}
+popd
+
+%files
+%{_bindir}/*
+%{_libdir}/libembdinput.a
+
+%changelog
+* Wed Aug 16 2023 zhoupengcheng <zhoupengcheng11@huawei.com> - 20230815-1
+- Init package
+