package/llama-cpp: new package

Add a package for llama.cpp, a C/C++ LLM inference library, used in
popular projects like Ollama, RamaLama, and more.

Signed-off-by: Joseph Kogut <joseph.kogut@gmail.com>
[Julien:
 - add a Config.in comment justifying the dynamic libraries for uclibc
 - add missing conditions in Config.in toolchain dependencies
]
Signed-off-by: Julien Olivain <ju.o@free.fr>

DEVELOPERS

@@ -1754,6 +1754,7 @@ F:	package/at-spi2-core/
 F:	package/earlyoom/
 F:	package/gconf/
 F:	package/libnss/
+F:	package/llama-cpp/
 F:	package/llvm-project/clang/
 F:	package/llvm-project/lld/
 F:	package/llvm-project/llvm/

package/Config.in

@@ -2290,6 +2290,7 @@ comment "linux-pam plugins"
 	source "package/libpam-tacplus/Config.in"
 endif
 	source "package/liquid-dsp/Config.in"
+	source "package/llama-cpp/Config.in"
 	source "package/llvm-project/llvm/Config.in"
 	source "package/lttng-libust/Config.in"
 	source "package/matio/Config.in"

package/llama-cpp/Config.in

@@ -0,0 +1,51 @@
+config BR2_PACKAGE_LLAMA_CPP_ARCH_SUPPORTS
+	bool
+	default y
+	depends on !BR2_s390x_z13 # ggml requires z14 or higher
+
+config BR2_PACKAGE_LLAMA_CPP
+	bool "llama.cpp"
+	depends on BR2_INSTALL_LIBSTDCPP
+	depends on BR2_PACKAGE_LLAMA_CPP_ARCH_SUPPORTS
+	depends on BR2_TOOLCHAIN_HAS_THREADS
+	depends on BR2_TOOLCHAIN_GCC_AT_LEAST_9
+	# llama.cpp needs libexecinfo when built with uclibc,
+	# and libexecinfo needs dynamic libraries.
+	depends on !BR2_TOOLCHAIN_USES_UCLIBC \
+		|| (BR2_TOOLCHAIN_USES_UCLIBC && !BR2_STATIC_LIBS)
+	depends on BR2_USE_WCHAR
+	select BR2_PACKAGE_LIBEXECINFO if BR2_TOOLCHAIN_USES_UCLIBC
+	help
+	  LLM inference in C/C++
+
+	  https://github.com/ggml-org/llama.cpp
+
+if BR2_PACKAGE_LLAMA_CPP
+
+config BR2_PACKAGE_LLAMA_CPP_TOOLS
+	bool "Enable tools"
+	help
+	  Build CLI tools like llama-cli, llama-bench, etc.
+
+config BR2_PACKAGE_LLAMA_CPP_SERVER
+	bool "Enable server"
+	help
+	  Build OpenAI API-compatible web server, llama-server.
+
+config BR2_PACKAGE_LLAMA_CPP_VULKAN
+	bool "Vulkan support"
+	depends on !BR2_ARM_CPU_ARMV5
+	depends on !BR2_STATIC_LIBS # vulkan-loader
+	select BR2_PACKAGE_VULKAN_LOADER
+	help
+	  Enable Vulkan backend for GPU acceleration.
+
+endif
+
+comment "llama-cpp needs a toolchain w/ C++, wchar, threads, and gcc >= 9"
+	depends on !BR2_INSTALL_LIBSTDCPP || !BR2_USE_WCHAR \
+		|| !BR2_TOOLCHAIN_HAS_THREADS \
+		|| !BR2_TOOLCHAIN_GCC_AT_LEAST_9
+
+comment "llama-cpp needs a uclibc toolchain w/ dynamic library"
+	depends on BR2_TOOLCHAIN_USES_UCLIBC && BR2_STATIC_LIBS

package/llama-cpp/llama-cpp.hash

@@ -0,0 +1,4 @@
+# Locally calculated
+sha256  c108fadd61d34da6ff2cfdf085821ff03a45acde2245d9eeeba9358482b305c3  b6865.tar.gz
+# License
+sha256  e562a2ddfaf8280537795ac5ecd34e3012b6582a147ef69ba6a6a5c08c84757d  LICENSE

package/llama-cpp/llama-cpp.mk

@@ -0,0 +1,70 @@
+################################################################################
+#
+# llama.cpp
+#
+################################################################################
+
+LLAMA_CPP_VERSION = b6865
+LLAMA_CPP_SOURCE = $(LLAMA_CPP_VERSION).tar.gz
+LLAMA_CPP_SITE = https://github.com/ggml-org/llama.cpp/archive/refs/tags
+LLAMA_CPP_LICENSE = MIT
+LLAMA_CPP_LICENSE_FILES = LICENSE
+LLAMA_CPP_CPE_ID_VENDOR = ggml
+LLAMA_CPP_CPE_ID_PRODUCT = llama.cpp
+LLAMA_CPP_INSTALL_STAGING = YES
+LLAMA_CPP_CONF_OPTS = \
+	-DLLAMA_BUILD_TESTS=OFF \
+	-DLLAMA_BUILD_EXAMPLES=OFF \
+	-DLLAMA_FATAL_WARNINGS=OFF
+
+ifeq ($(BR2_PACKAGE_LIBEXECINFO),y)
+LLAMA_CPP_DEPENDENCIES += libexecinfo
+LLAMA_CPP_LDFLAGS += -lexecinfo
+endif
+
+ifeq ($(BR2_TOOLCHAIN_HAS_LIBATOMIC),y)
+LLAMA_CPP_LDFLAGS += -latomic
+endif
+
+LLAMA_CPP_CONF_OPTS += \
+	-DCMAKE_EXE_LINKER_FLAGS="$(LLAMA_CPP_LDFLAGS)"
+
+ifeq ($(BR2_STATIC_LIBS),y)
+LLAMA_CPP_CONF_OPTS += -DBUILD_SHARED_LIBS=OFF \
+		       -DCMAKE_POSITION_INDEPENDENT_CODE=ON
+endif
+
+ifeq ($(BR2_PACKAGE_LIBCURL),y)
+LLAMA_CPP_CONF_OPTS += -DLLAMA_CURL=ON
+LLAMA_CPP_DEPENDENCIES += libcurl
+else
+LLAMA_CPP_CONF_OPTS += -DLLAMA_CURL=OFF
+endif
+
+ifeq ($(BR2_PACKAGE_LLAMA_CPP_TOOLS),y)
+LLAMA_CPP_CONF_OPTS += -DLLAMA_BUILD_TOOLS=ON
+else
+LLAMA_CPP_CONF_OPTS += -DLLAMA_BUILD_TOOLS=OFF
+endif
+
+ifeq ($(BR2_PACKAGE_LLAMA_CPP_SERVER),y)
+LLAMA_CPP_CONF_OPTS += -DLLAMA_BUILD_SERVER=ON
+else
+LLAMA_CPP_CONF_OPTS += -DLLAMA_BUILD_SERVER=OFF
+endif
+
+ifeq ($(BR2_PACKAGE_LLAMA_CPP_VULKAN),y)
+LLAMA_CPP_DEPENDENCIES += vulkan-loader
+LLAMA_CPP_CONF_OPTS += -DGGML_VULKAN=ON
+else
+LLAMA_CPP_CONF_OPTS += -DGGML_VULKAN=OFF
+endif
+
+ifeq ($(BR2_PACKAGE_OPENBLAS),y)
+LLAMA_CPP_DEPENDENCIES += openblas
+LLAMA_CPP_CONF_OPTS += -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+else
+LLAMA_CPP_CONF_OPTS += -DGGML_BLAS=OFF
+endif
+
+$(eval $(cmake-package))