| 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 |
