llama.cpp/examples/llava/CMakeLists.txt

53 lines
1.9 KiB
CMake
Raw Normal View History

add_library(llava OBJECT
llava.cpp
llava.h
clip.cpp
clip.h
)
target_link_libraries(llava PRIVATE ggml llama ${CMAKE_THREAD_LIBS_INIT})
target_include_directories(llava PUBLIC .)
target_include_directories(llava PUBLIC ../..)
target_include_directories(llava PUBLIC ../../common)
target_compile_features(llava PRIVATE cxx_std_17)
add_library(llava_static STATIC $<TARGET_OBJECTS:llava>)
if (BUILD_SHARED_LIBS)
set_target_properties(llava PROPERTIES POSITION_INDEPENDENT_CODE ON)
target_compile_definitions(llava PRIVATE LLAMA_SHARED LLAMA_BUILD)
add_library(llava_shared SHARED $<TARGET_OBJECTS:llava>)
target_link_libraries(llava_shared PRIVATE ggml llama ${CMAKE_THREAD_LIBS_INIT})
install(TARGETS llava_shared LIBRARY)
endif()
if (NOT MSVC)
target_compile_options(llava PRIVATE -Wno-cast-qual) # stb_image.h
endif()
if(TARGET BUILD_INFO)
add_dependencies(llava BUILD_INFO)
endif()
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) * `main`/`server`: rename to `llama` / `llama-server` for consistency w/ homebrew * server: update refs -> llama-server gitignore llama-server * server: simplify nix package * main: update refs -> llama fix examples/main ref * main/server: fix targets * update more names * Update build.yml * rm accidentally checked in bins * update straggling refs * Update .gitignore * Update server-llm.sh * main: target name -> llama-cli * Prefix all example bins w/ llama- * fix main refs * rename {main->llama}-cmake-pkg binary * prefix more cmake targets w/ llama- * add/fix gbnf-validator subfolder to cmake * sort cmake example subdirs * rm bin files * fix llama-lookup-* Makefile rules * gitignore /llama-* * rename Dockerfiles * rename llama|main -> llama-cli; consistent RPM bin prefixes * fix some missing -cli suffixes * rename dockerfile w/ llama-cli * rename(make): llama-baby-llama * update dockerfile refs * more llama-cli(.exe) * fix test-eval-callback * rename: llama-cli-cmake-pkg(.exe) * address gbnf-validator unused fread warning (switched to C++ / ifstream) * add two missing llama- prefixes * Updating docs for eval-callback binary to use new `llama-` prefix. * Updating a few lingering doc references for rename of main to llama-cli * Updating `run-with-preset.py` to use new binary names. Updating docs around `perplexity` binary rename. * Updating documentation references for lookup-merge and export-lora * Updating two small `main` references missed earlier in the finetune docs. * Update apps.nix * update grammar/README.md w/ new llama-* names * update llama-rpc-server bin name + doc * Revert "update llama-rpc-server bin name + doc" This reverts commit e474ef1df481fd8936cd7d098e3065d7de378930. * add hot topic notice to README.md * Update README.md * Update README.md * rename gguf-split & quantize bins refs in **/tests.sh --------- Co-authored-by: HanClinto <hanclinto@gmail.com>
2024-06-12 23:41:52 +00:00
set(TARGET llama-llava-cli)
add_executable(${TARGET} llava-cli.cpp)
set_target_properties(${TARGET} PROPERTIES OUTPUT_NAME llama-llava-cli)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE common llava ${CMAKE_THREAD_LIBS_INIT})
target_compile_features(${TARGET} PRIVATE cxx_std_17)
llava : support MiniCPM-V-2.5 (#7599) * init * rename * add run android for termux in readme * add android readme * add instructions in readme * change name in readme * Update README.md * fixed line * add result in readme * random pos_embed * add positions index * change for ollama * change for ollama * better pos_embed in clip * support ollama * updata cmakelist * updata cmakelist * rename wrapper * clear code * replace and organize code * add link * sync master * fix warnings * fix warnings * fix bug in bicubic resize when need resize iamge smaller * receive review comments and modify * receive review comments and modify * put all code into llava dir * fix quality problem in pr code * change n_layer * add space in "-1" * imitate reshape bug of python code * fix bug in clip * fix issues for merging * fix llama-minicpmv-cli in cmake file * change pr readme * fix code review * remove in line 33 directory in the /cmakelists.txt (not in example, in the main dir * fix cmakefile * add warn * fix KEY_HAS_MINICPMV_PROJ * remove load_image_size into clip_ctx * remove the extern "C", MINICPMV_API * fix uhd code for review comment * delete minicpmv-wrapper in pr * remove uhd_image_embed * Modify 2 notes * clip : style changes * del common.h in clip * fix Type-Check error * fix Type-Check error * fix Type-Check error * fix Type-Check error * fix makefile error * fix ubuntu-make error * try fix clip * try fix 1 --------- Co-authored-by: Hongji Zhu <fireyoucan@gmail.com> Co-authored-by: harvestingmoon <leewenyeong@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-08-09 10:33:53 +00:00
set(TARGET llama-minicpmv-cli)
add_executable(${TARGET} minicpmv-cli.cpp)
set_target_properties(${TARGET} PROPERTIES OUTPUT_NAME llama-minicpmv-cli)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE common llava ${CMAKE_THREAD_LIBS_INIT})
target_compile_features(${TARGET} PRIVATE cxx_std_17)
llama : add Qwen2VL support + multimodal RoPE (#10361) * Barebone Qwen2VL LLM convertor * Add Qwen2VL cli entrypoint * [WIP] add qwen2vl arch * Verify m-rope output * Add vl-rope/2d-rope support for qwen2vl ViT * update qwen2vl cli tool * update 5D tensor op workaround * [WIP] qwen2vl vision model * make batch and clip utils compatible with qwen2vl * [WIP] create inference workflow, gguf convert script but fix * correcting vision-rope behavior, add the missing last layer back to ViT * add arg parser to qwen2vl_surgery * replace variable size array with vector * cuda-gdb cmake preset * add fp32 mrope, vision rope kernel * add fp16 support for qwen2vl and m-rope * add `GGML_ROPE_TYPE_MROPE`, `GGML_ROPE_TYPE_VISION` * fix rope op mode switching, out dated func args * update `llama_hparams` * update to keep up stream changes * resolve linter, test errors * add makefile entry, update speical image padding token * add mrope unit test, fix few compiler warnings * rename `mrope` related function, params * minor updates on debug util, bug fixs * add `m-rope` testcase to `test-backend-ops` * Apply suggestions from code review Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * fix traililng whitespce * store `llama_hparams.rope_sections` with fixed size array * update position id tensor size check in GGML_OP_ROPE * minor updates * update `ggml_backend_*_supports_op` of unsupported backends * remote old `rope_section` compare operator --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-12-14 12:43:46 +00:00
set(TARGET llama-qwen2vl-cli)
add_executable(${TARGET} qwen2vl-cli.cpp)
set_target_properties(${TARGET} PROPERTIES OUTPUT_NAME llama-qwen2vl-cli)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE common llava ${CMAKE_THREAD_LIBS_INIT})
target_compile_features(${TARGET} PRIVATE cxx_std_17)