mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +00:00
9ee72225dc
* Implement function calling / tools for ik_llama.cpp for Kimi K2
* Implement basic tool choice
* Backport llama.cpp tool calls support
* Enhance function calls with improved chat parser and string utilities
- Add new chat.h/chat.cpp and chat-parser.h/chat-parser.cpp for better chat handling
- Improve function calls parsing with fallback to llama.cpp builder pattern
- Add string utility functions (starts_with, ends_with, find_partial_stop)
- Update README with function calls testing instructions
- Enhance Kimi K2 parser and function calls documentation
- Add comprehensive test suite for function calls
- Update CMakeLists.txt and Makefile for new components
* Enhance function calling with unified streaming and parser improvements
- Fix streaming content cleanup to prevent function syntax in output
- Unify content extraction patterns with llama.cpp approach
- Improve Kimi K2 parser robustness and partial content handling
- Add comprehensive test coverage for function call scenarios
- Optimize chat message parsing and diff computation
* Replace hardcoded values in kimi_k2_parser.hpp with named constants
- Add compile-time constants for all token format markers
- Add compile-time constants for XML format markers
- Add compile-time constants for simple format patterns
- Replace all hardcoded string literals with named constants
- Use compile-time length calculation to avoid manual counting
- Improve maintainability and reduce magic numbers throughout parser
* Fix duplicate common_chat_parse definition
- Remove duplicate implementation from chat-parser.cpp
- Keep single implementation in chat.cpp following llama.cpp patterns
- Resolves linker error: multiple definition of common_chat_parse
* Fix JSON assertion failure in function call parsing
- Add proper validation that 'function' field is an object before accessing nested keys
- Handle missing 'arguments' field gracefully with default "{}"
- Prevents crash when parsing malformed tool call JSON structures
* Add comprehensive Qwen3 XML tool calling support with unit tests
- Implement Qwen3 XML parser with <tool_call>{"name": "func", "arguments": {...}}</tool_call> format
- Add model detection and routing for Qwen3 vs Kimi-K2 formats
- Create 8 comprehensive unit tests covering parsing, streaming, error handling
- Fix token format cleaning bug in kimi_k2_parser.hpp processing order
- Remove progressive parsing code and related utilities
- Add tool injection support for Qwen3 format in server utils
* Add DeepSeek R1 function calling support with comprehensive unit tests
- Implement complete DeepSeek R1 tool call parsing in common_chat_parser.cpp
- Add DeepSeek R1 model detection and tool injection in deepseek_r1_tools.hpp
- Update function_calls.hpp with DeepSeek R1 integration and content extraction
- Update documentation to reflect support for Kimi-K2, Qwen3, and DeepSeek R1 models
- Add comprehensive unit tests for DeepSeek R1 reasoning, tool calls, and integration
- Port exact implementation patterns from original llama.cpp for compatibility
Key features:
- Native DeepSeek R1 format: <｜tool▁calls▁begin｜>function<｜tool▁sep｜>name```json{}```<｜tool▁call▁end｜><｜tool▁calls▁end｜>
- Reasoning content extraction from <think>...</think> tags
- Multiple tool calls support with separate call blocks
- Model detection for deepseek-r1, deepseek_r1 naming patterns
- Integration with incremental parsing and streaming support
* Add partial parsing support for JSON and regex
- json-partial.h/cpp: JSON partial parsing functionality
- regex-partial.h/cpp: Regex partial parsing functionality
* Add format_chat integration tests for Qwen3 tool injection
- Add test_qwen3_format_chat_integration() to validate tool injection pipeline
- Test tool injection conditions and system message enhancement
- Verify JSON formatting and anti-preamble instructions
- Add comprehensive test documentation
Tests confirm tool injection works correctly - conversational preamble
issue is not in ik_llama.cpp but likely in UI configuration.
* Fix Qwen3 tool call parsing - pass model name to parser
Server was not passing model name to parse_chat_message_incremental(),
causing Qwen3 to fall back to Kimi-K2 parser and return tool calls
as content instead of proper tool_calls array.
* Fix non-streaming path to use model-specific parsing
Non-streaming responses were hardcoded to use Kimi-K2 format,
causing Qwen3 XML tool calls to be returned as content instead
of proper tool_calls array. Now uses same model detection as
streaming path for consistency.
97 lines
2.9 KiB
CMake
97 lines
2.9 KiB
CMake
# common
|
|
|
|
find_package(Threads REQUIRED)
|
|
|
|
# Build info header
|
|
#
|
|
|
|
if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/../.git")
|
|
set(GIT_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../.git")
|
|
|
|
# Is git submodule
|
|
if(NOT IS_DIRECTORY "${GIT_DIR}")
|
|
file(READ ${GIT_DIR} REAL_GIT_DIR_LINK)
|
|
string(REGEX REPLACE "gitdir: (.*)\n$" "\\1" REAL_GIT_DIR ${REAL_GIT_DIR_LINK})
|
|
string(FIND "${REAL_GIT_DIR}" "/" SLASH_POS)
|
|
if (SLASH_POS EQUAL 0)
|
|
set(GIT_DIR "${REAL_GIT_DIR}")
|
|
else()
|
|
set(GIT_DIR "${CMAKE_CURRENT_SOURCE_DIR}/../${REAL_GIT_DIR}")
|
|
endif()
|
|
endif()
|
|
|
|
if(EXISTS "${GIT_DIR}/index")
|
|
set(GIT_INDEX "${GIT_DIR}/index")
|
|
else()
|
|
message(WARNING "Git index not found in git repository.")
|
|
set(GIT_INDEX "")
|
|
endif()
|
|
else()
|
|
message(WARNING "Git repository not found; to enable automatic generation of build info, make sure Git is installed and the project is a Git repository.")
|
|
set(GIT_INDEX "")
|
|
endif()
|
|
|
|
# Add a custom command to rebuild build-info.cpp when .git/index changes
|
|
add_custom_command(
|
|
OUTPUT "${CMAKE_CURRENT_SOURCE_DIR}/build-info.cpp"
|
|
COMMENT "Generating build details from Git"
|
|
COMMAND ${CMAKE_COMMAND} -DMSVC=${MSVC} -DCMAKE_C_COMPILER_VERSION=${CMAKE_C_COMPILER_VERSION}
|
|
-DCMAKE_C_COMPILER_ID=${CMAKE_C_COMPILER_ID} -DCMAKE_VS_PLATFORM_NAME=${CMAKE_VS_PLATFORM_NAME}
|
|
-DCMAKE_C_COMPILER=${CMAKE_C_COMPILER} -P "${CMAKE_CURRENT_SOURCE_DIR}/cmake/build-info-gen-cpp.cmake"
|
|
WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}/.."
|
|
DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/build-info.cpp.in" ${GIT_INDEX}
|
|
VERBATIM
|
|
)
|
|
set(TARGET build_info)
|
|
add_library(${TARGET} OBJECT build-info.cpp)
|
|
if (BUILD_SHARED_LIBS)
|
|
set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON)
|
|
endif()
|
|
|
|
set(TARGET common)
|
|
|
|
add_library(${TARGET} STATIC
|
|
base64.hpp
|
|
common.h
|
|
common.cpp
|
|
chat.h
|
|
chat.cpp
|
|
chat-parser.h
|
|
chat-parser.cpp
|
|
json-partial.h
|
|
json-partial.cpp
|
|
regex-partial.h
|
|
regex-partial.cpp
|
|
sampling.h
|
|
sampling.cpp
|
|
console.h
|
|
console.cpp
|
|
grammar-parser.h
|
|
grammar-parser.cpp
|
|
json.hpp
|
|
json-schema-to-grammar.cpp
|
|
train.h
|
|
train.cpp
|
|
ngram-cache.h
|
|
ngram-cache.cpp
|
|
)
|
|
|
|
if (BUILD_SHARED_LIBS)
|
|
set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON)
|
|
endif()
|
|
|
|
set(LLAMA_COMMON_EXTRA_LIBS build_info)
|
|
|
|
# Use curl to download model url
|
|
if (LLAMA_CURL)
|
|
find_package(CURL REQUIRED)
|
|
add_definitions(-DLLAMA_USE_CURL)
|
|
include_directories(${CURL_INCLUDE_DIRS})
|
|
find_library(CURL_LIBRARY curl REQUIRED)
|
|
set(LLAMA_COMMON_EXTRA_LIBS ${LLAMA_COMMON_EXTRA_LIBS} ${CURL_LIBRARY})
|
|
endif ()
|
|
|
|
target_include_directories(${TARGET} PUBLIC .)
|
|
target_compile_features (${TARGET} PUBLIC cxx_std_11)
|
|
target_link_libraries (${TARGET} PRIVATE ${LLAMA_COMMON_EXTRA_LIBS} PUBLIC llama Threads::Threads)
|