Skip to content

feat: native llama.cpp integration in cortex-daemon replacing ollama process #766

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Ishant5436 wants to merge 6 commits into
base: main
Choose a base branch
from
Open

feat: native llama.cpp integration in cortex-daemon replacing ollama process #766

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
4b12fd5
feat: native llama.cpp integration in cortex-daemon replacing ollama …
Ishant5436 Jun 10, 2026
9455d88
chore: remove build dir and address CMake review feedback
Ishant5436 Jun 10, 2026
00e3d03
Address CodeRabbit feedback: handle NUL bytes, string allocations, ge…
Ishant5436 Jun 10, 2026
101c81e
Fix minor review feedback from CodeRabbit
Ishant5436 Jun 10, 2026
ffe6c18
chore: remove unused n_vocab variable
Ishant5436 Jun 10, 2026
03a46da
fix: resolve AI feedback on cortex-daemon bridging
Ishant5436 Jun 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
113 changes: 113 additions & 0 deletions cortex-daemon/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,113 @@
cmake_minimum_required(VERSION 3.20)
project(cortex-daemon VERSION 1.0.0 LANGUAGES C CXX)

set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_C_STANDARD 11)

# Build options
option(CORTEX_STATIC_LINK "Link llama.cpp statically" ON)
option(CORTEX_METAL "Enable Apple Metal GPU (macOS)" OFF)
option(CORTEX_CUDA "Enable NVIDIA CUDA GPU" OFF)
option(CORTEX_VULKAN "Enable Vulkan GPU" OFF)
option(CORTEX_AVX2 "Enable AVX2 SIMD (x86_64)" OFF)

# Detect architecture
if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64|aarch64")
set(ARCH_ARM64 TRUE)
message(STATUS "Target: ARM64")
elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64|amd64|AMD64")
set(ARCH_X86_64 TRUE)
message(STATUS "Target: x86_64")
else()
message(FATAL_ERROR "Unsupported architecture: ${CMAKE_SYSTEM_PROCESSOR}")
endif()
Comment on lines +22 to +24

@gemini-code-assist gemini-code-assist Bot Jun 10, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To support portable thread linking, we should find the Threads package using find_package(Threads REQUIRED).

else()
    message(FATAL_ERROR "Unsupported architecture: ${CMAKE_SYSTEM_PROCESSOR}")
endif()

find_package(Threads REQUIRED)


# ── llama.cpp submodule ──────────────────────────────────────────────────────
set(LLAMA_CPP_DIR "${CMAKE_SOURCE_DIR}/vendor/llama.cpp")

if(NOT EXISTS "${LLAMA_CPP_DIR}/CMakeLists.txt")
message(FATAL_ERROR
"llama.cpp submodule not found. Run:\n"
" git submodule update --init --recursive")
endif()

# Forward GPU options into llama.cpp's own build
set(LLAMA_METAL ${CORTEX_METAL} CACHE BOOL "" FORCE)
set(LLAMA_CUDA ${CORTEX_CUDA} CACHE BOOL "" FORCE)
set(LLAMA_VULKAN ${CORTEX_VULKAN} CACHE BOOL "" FORCE)

# Build llama.cpp as a library only (no CLI executables)
set(LLAMA_BUILD_EXAMPLES OFF CACHE BOOL "" FORCE)
set(LLAMA_BUILD_TESTS OFF CACHE BOOL "" FORCE)
set(LLAMA_BUILD_SERVER OFF CACHE BOOL "" FORCE)

add_subdirectory(${LLAMA_CPP_DIR} llama_cpp_build)

# ── Cortex inference library ─────────────────────────────────────────────────
set(INFERENCE_SOURCES
src/inference/llama_engine.cpp
src/inference/inference_manager.cpp
src/bindings/llama_c_bridge.cpp
src/models/model_registry.cpp
)

if(CORTEX_STATIC_LINK)
add_library(cortex_inference STATIC ${INFERENCE_SOURCES})
else()
add_library(cortex_inference SHARED ${INFERENCE_SOURCES})
set_target_properties(cortex_inference PROPERTIES
VERSION ${PROJECT_VERSION}
SOVERSION 1
)
endif()

target_include_directories(cortex_inference
PUBLIC
$<BUILD_INTERFACE:${CMAKE_SOURCE_DIR}/src>
$<INSTALL_INTERFACE:include/cortex>
PRIVATE
${LLAMA_CPP_DIR}
${LLAMA_CPP_DIR}/common
)

# Use portable Threads package
find_package(Threads REQUIRED)

target_link_libraries(cortex_inference
PUBLIC llama Threads::Threads
PRIVATE $<$<PLATFORM_ID:Linux>:dl>
)
Comment on lines +77 to +80

@gemini-code-assist gemini-code-assist Bot Jun 10, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Hardcoding pthread is not portable across all platforms. The standard and portable way to link threads in CMake is to use find_package(Threads REQUIRED) and link against Threads::Threads.

target_link_libraries(cortex_inference
    PUBLIC  llama
    PRIVATE $<$<PLATFORM_ID:Linux>:Threads::Threads>
            $<$<PLATFORM_ID:Linux>:dl>
)


# Conditional compiler flags for non-MSVC
if(NOT MSVC)
target_compile_options(cortex_inference PRIVATE
-O3
-ffast-math
-fvisibility=hidden
$<$<CXX_COMPILER_ID:GNU,Clang>:-Wall -Wextra -Wpedantic>
)

# Restrict ARM64 flags to non-Apple to prevent macOS build failures
if(ARCH_ARM64)
if(NOT APPLE)
target_compile_options(cortex_inference PRIVATE -mcpu=native)
endif()
elseif(ARCH_X86_64)
# Avoid -march=native by default to ensure binary portability
target_compile_options(cortex_inference PRIVATE
$<$<BOOL:${CORTEX_AVX2}>:-mavx2 -mfma>
)
endif()
endif()

# ── Cortex daemon executable ─────────────────────────────────────────────────
add_executable(cortexd src/main.cpp)
target_link_libraries(cortexd PRIVATE cortex_inference)

# ── Tests ────────────────────────────────────────────────────────────────────
# Guard enable_testing() to prevent affecting parent projects
if(CMAKE_PROJECT_NAME STREQUAL PROJECT_NAME)
enable_testing()
add_subdirectory(tests)
endif()
Loading
Loading