8c146a8366
* convert: add dsv4 conversion * add basic setup * add llm_graph_input_dsv4 * add save-load state * add sinkhorn eps - correction by @fairydreaming * add rope fix * cleanup dead code * fix bugs * support pro model: added by @fairydreaming * remove redundant V cache * Chat template * remove debugging leftovers * Add mechanism for inlining templates based on architecture * s/deepseek-v4-flash/deepseek4/g * s/deepseek-v4-flash/deepseek4/g continued * enable graph reuse * enable FA * fix test llama archs * rename * compatibility with antirez ds4 GGUFs * simplified set_gguf_parameters() by calling super class method, replaced moe.score_func with expert_gating_func. * reserve worst-case kv-cache * revert max split inputs * address review comments * add padding to enable FA * pad only the final value of plan.n_kv to 256 * remove built-in cpp chat template * cont: remove cpp built-in template * rm outdated test * replace ggml_view_3d() with ggml_reshape_3d() Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * only support n_seq=1 for now * remove unused var * cont: remove unused var * use scale bias * use correct ptr for can_reuse * remove gen-chat-inline-templates.py * simplify graph reuse * cont: cleanup * remove unused inputs * enable partial checkpointing * add correct shape for kq_mask + set llama_model_n_swa to 0 for dsv4 * precompute source_idx + add comment about dummy write * support multi-seq * remove restored_trim_pos * use split_equal when possible * fix indent * address review comments * use LLM_KV * fix ci --------- Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com> Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
63 lines
1.7 KiB
CMake
63 lines
1.7 KiB
CMake
llama_add_compile_flags()
|
|
|
|
#
|
|
# libraries
|
|
#
|
|
|
|
# llama
|
|
|
|
file(GLOB LLAMA_MODELS_SOURCES "models/*.cpp")
|
|
|
|
add_library(llama
|
|
../include/llama.h
|
|
llama.cpp
|
|
llama-adapter.cpp
|
|
llama-arch.cpp
|
|
llama-batch.cpp
|
|
llama-chat.cpp
|
|
llama-context.cpp
|
|
llama-cparams.cpp
|
|
llama-grammar.cpp
|
|
llama-graph.cpp
|
|
llama-hparams.cpp
|
|
llama-impl.cpp
|
|
llama-io.cpp
|
|
llama-kv-cache.cpp
|
|
llama-kv-cache-iswa.cpp
|
|
llama-kv-cache-dsa.cpp
|
|
llama-kv-cache-dsv4.cpp
|
|
llama-memory.cpp
|
|
llama-memory-hybrid.cpp
|
|
llama-memory-hybrid-iswa.cpp
|
|
llama-memory-recurrent.cpp
|
|
llama-mmap.cpp
|
|
llama-model-loader.cpp
|
|
llama-model-saver.cpp
|
|
llama-model.cpp
|
|
llama-quant.cpp
|
|
llama-sampler.cpp
|
|
llama-vocab.cpp
|
|
unicode-data.cpp
|
|
unicode.cpp
|
|
unicode.h
|
|
${LLAMA_MODELS_SOURCES}
|
|
)
|
|
|
|
set_target_properties(llama PROPERTIES
|
|
VERSION ${LLAMA_INSTALL_VERSION}
|
|
SOVERSION 0
|
|
MACHO_CURRENT_VERSION 0 # keep macOS linker from seeing oversized version number
|
|
)
|
|
|
|
target_include_directories(llama PRIVATE .)
|
|
target_include_directories(llama PUBLIC ../include)
|
|
target_compile_features (llama PRIVATE 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()
|