e0dbec0bc6
* llama : refactor llama_context, llama_kv_cache, llm_build_context ggml-ci * graph : don't mutate the KV cache during defrag ggml-ci * context : reduce virtuals + remove test function ggml-ci * context : move interface implementation to source file + factory ggml-ci * graph : move KV cache build functions to llama_context impl ggml-ci * graph : remove model reference from build_pooling ggml-ci * graph : remove llama_model reference ggml-ci * kv_cache : provide rope factors ggml-ci * graph : rework inputs to use only unique_ptr, remove attn input abstraction ggml-ci * context : remove llama_context_i abstraction ggml-ci * context : clean-up ggml-ci * graph : clean-up ggml-ci * llama : remove redundant keywords (struct, enum) ggml-ci * model : adapt gemma3 ggml-ci * graph : restore same attention ops as on master ggml-ci * llama : remove TODO + fix indent ggml-ci
45 lines
1.1 KiB
CMake
45 lines
1.1 KiB
CMake
llama_add_compile_flags()
|
|
|
|
#
|
|
# libraries
|
|
#
|
|
|
|
# llama
|
|
|
|
add_library(llama
|
|
../include/llama.h
|
|
llama.cpp
|
|
llama-adapter.cpp
|
|
llama-arch.cpp
|
|
llama-batch.cpp
|
|
llama-chat.cpp
|
|
llama-context.cpp
|
|
llama-grammar.cpp
|
|
llama-graph.cpp
|
|
llama-hparams.cpp
|
|
llama-impl.cpp
|
|
llama-io.cpp
|
|
llama-kv-cache.cpp
|
|
llama-memory.cpp
|
|
llama-mmap.cpp
|
|
llama-model-loader.cpp
|
|
llama-model.cpp
|
|
llama-quant.cpp
|
|
llama-sampling.cpp
|
|
llama-vocab.cpp
|
|
unicode-data.cpp
|
|
unicode.cpp
|
|
unicode.h
|
|
)
|
|
|
|
target_include_directories(llama PUBLIC . ../include ../common)
|
|
target_compile_features (llama PUBLIC cxx_std_17) # don't bump
|
|
|
|
target_link_libraries(llama PUBLIC ggml)
|
|
|
|
if (BUILD_SHARED_LIBS)
|
|
set_target_properties(llama PROPERTIES POSITION_INDEPENDENT_CODE ON)
|
|
target_compile_definitions(llama PRIVATE LLAMA_BUILD)
|
|
target_compile_definitions(llama PUBLIC LLAMA_SHARED)
|
|
endif()
|