mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-13 10:57:15 +00:00
bea04522ff
* Sqashed: llama-model.cpp refactoring * Fix formatting of attn / ffn / ffn_moe calls * Fix import regression / unify spacing in models.h * totally DID NOT miss those! * Add missing qwen3vl(moe) models * Add missing new .cpp files to build * Remove extra semicolons * Editor checker * Update src/models/models.h Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
145 lines
4.2 KiB
CMake
145 lines
4.2 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-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-memory.cpp
|
|
llama-memory-hybrid.cpp
|
|
llama-memory-recurrent.cpp
|
|
llama-mmap.cpp
|
|
llama-model-loader.cpp
|
|
llama-model-saver.cpp
|
|
llama-model.cpp
|
|
llama-quant.cpp
|
|
llama-sampling.cpp
|
|
llama-vocab.cpp
|
|
unicode-data.cpp
|
|
unicode.cpp
|
|
unicode.h
|
|
models/apertus.cpp
|
|
models/arcee.cpp
|
|
models/arctic.cpp
|
|
models/arwkv7.cpp
|
|
models/baichuan.cpp
|
|
models/bailingmoe.cpp
|
|
models/bailingmoe2.cpp
|
|
models/bert.cpp
|
|
models/bitnet.cpp
|
|
models/bloom.cpp
|
|
models/chameleon.cpp
|
|
models/chatglm.cpp
|
|
models/codeshell.cpp
|
|
models/cogvlm.cpp
|
|
models/cohere2-iswa.cpp
|
|
models/command-r.cpp
|
|
models/dbrx.cpp
|
|
models/deci.cpp
|
|
models/deepseek.cpp
|
|
models/deepseek2.cpp
|
|
models/dots1.cpp
|
|
models/dream.cpp
|
|
models/ernie4-5-moe.cpp
|
|
models/ernie4-5.cpp
|
|
models/exaone.cpp
|
|
models/exaone4.cpp
|
|
models/falcon-h1.cpp
|
|
models/falcon.cpp
|
|
models/gemma-embedding.cpp
|
|
models/gemma.cpp
|
|
models/gemma2-iswa.cpp
|
|
models/gemma3-iswa.cpp
|
|
models/gemma3n-iswa.cpp
|
|
models/glm4-moe.cpp
|
|
models/glm4.cpp
|
|
models/gpt2.cpp
|
|
models/gptneox.cpp
|
|
models/granite-hybrid.cpp
|
|
models/granite.cpp
|
|
models/grok.cpp
|
|
models/grovemoe.cpp
|
|
models/hunyuan-dense.cpp
|
|
models/hunyuan-moe.cpp
|
|
models/internlm2.cpp
|
|
models/jais.cpp
|
|
models/jamba.cpp
|
|
models/lfm2.cpp
|
|
models/llada-moe.cpp
|
|
models/llada.cpp
|
|
models/llama-iswa.cpp
|
|
models/llama.cpp
|
|
models/mamba.cpp
|
|
models/minicpm3.cpp
|
|
models/minimax-m2.cpp
|
|
models/mpt.cpp
|
|
models/nemotron-h.cpp
|
|
models/nemotron.cpp
|
|
models/neo-bert.cpp
|
|
models/olmo.cpp
|
|
models/olmo2.cpp
|
|
models/olmoe.cpp
|
|
models/openai-moe-iswa.cpp
|
|
models/openelm.cpp
|
|
models/orion.cpp
|
|
models/phi2.cpp
|
|
models/phi3.cpp
|
|
models/plamo.cpp
|
|
models/plamo2.cpp
|
|
models/plm.cpp
|
|
models/qwen.cpp
|
|
models/qwen2.cpp
|
|
models/qwen2moe.cpp
|
|
models/qwen2vl.cpp
|
|
models/qwen3.cpp
|
|
models/qwen3vl.cpp
|
|
models/qwen3vl-moe.cpp
|
|
models/qwen3moe.cpp
|
|
models/refact.cpp
|
|
models/rwkv6-base.cpp
|
|
models/rwkv6.cpp
|
|
models/rwkv6qwen2.cpp
|
|
models/rwkv7-base.cpp
|
|
models/rwkv7.cpp
|
|
models/seed-oss.cpp
|
|
models/smallthinker.cpp
|
|
models/smollm3.cpp
|
|
models/stablelm.cpp
|
|
models/starcoder.cpp
|
|
models/starcoder2.cpp
|
|
models/t5-dec.cpp
|
|
models/t5-enc.cpp
|
|
models/wavtokenizer-dec.cpp
|
|
models/xverse.cpp
|
|
models/graph-context-mamba.cpp
|
|
)
|
|
|
|
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()
|