mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-26 19:55:04 +00:00
33eff40240
* server : (experimental) vision support via libmtmd * mtmd : add more api around mtmd_image_tokens * mtmd : add more api around mtmd_image_tokens * mtmd : ability to calc image hash * shared_ptr for mtmd_image_tokens * move hash to user-define ID (fixed) * abstract out the batch management * small fix * refactor logic adding tokens to batch * implement hashing image * use FNV hash, now hash bitmap instead of file data * allow decoding image embedding to be split into batches * rm whitespace * disable some features when mtmd is on * fix --no-mmproj-offload * mtmd_context_params no timings * refactor server_inp to server_tokens * fix the failing test case * init * wip * working version * add mtmd::bitmaps * add test target * rm redundant define * test: mtmd_input_chunks_free * rm outdated comment * fix merging issue * explicitly create mtmd::input_chunks * mtmd_input_chunk_copy * add clone() * improve server_input struct * clip : fix confused naming ffn_up and ffn_down * rm ffn_i/o/g naming * rename n_embd, n_ff * small fix * no check n_ff * fix detokenize * add const to various places * add warning about breaking changes * add c api * helper: use mtmd_image_tokens_get_n_pos * fix ctx_shift * fix name shadowing * more strict condition * support remote image_url * remote image_url log * add CI test * do not log base64 * add "has_multimodal" to /props * remove dangling image * speculative: use slot.cache_tokens.insert * Apply suggestions from code review Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * rm can_be_detokenized * on prmpt processing done, assert cache_tokens.size * handle_completions_impl returns void * adapt the new web ui * update docs and hot topics * rm assert * small fix (2) --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
52 lines
1.5 KiB
CMake
52 lines
1.5 KiB
CMake
set(TARGET llama-server)
|
|
|
|
option(LLAMA_SERVER_SSL "Build SSL support for the server" OFF)
|
|
|
|
include_directories(${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_BINARY_DIR})
|
|
|
|
if (MINGW)
|
|
# fix: https://github.com/ggml-org/llama.cpp/actions/runs/9651004652/job/26617901362?pr=8006
|
|
add_compile_definitions(_WIN32_WINNT=${GGML_WIN_VER})
|
|
endif()
|
|
|
|
set(TARGET_SRCS
|
|
server.cpp
|
|
utils.hpp
|
|
httplib.h
|
|
)
|
|
set(PUBLIC_ASSETS
|
|
index.html.gz
|
|
loading.html
|
|
)
|
|
|
|
foreach(asset ${PUBLIC_ASSETS})
|
|
set(input "${CMAKE_CURRENT_SOURCE_DIR}/public/${asset}")
|
|
set(output "${CMAKE_CURRENT_BINARY_DIR}/${asset}.hpp")
|
|
list(APPEND TARGET_SRCS ${output})
|
|
add_custom_command(
|
|
DEPENDS "${input}"
|
|
OUTPUT "${output}"
|
|
COMMAND "${CMAKE_COMMAND}" "-DINPUT=${input}" "-DOUTPUT=${output}" -P "${PROJECT_SOURCE_DIR}/scripts/xxd.cmake"
|
|
)
|
|
set_source_files_properties(${output} PROPERTIES GENERATED TRUE)
|
|
endforeach()
|
|
|
|
add_executable(${TARGET} ${TARGET_SRCS})
|
|
install(TARGETS ${TARGET} RUNTIME)
|
|
|
|
target_include_directories(${TARGET} PRIVATE ../llava)
|
|
target_include_directories(${TARGET} PRIVATE ${CMAKE_SOURCE_DIR})
|
|
target_link_libraries(${TARGET} PRIVATE common mtmd ${CMAKE_THREAD_LIBS_INIT})
|
|
|
|
if (LLAMA_SERVER_SSL)
|
|
find_package(OpenSSL REQUIRED)
|
|
target_link_libraries(${TARGET} PRIVATE OpenSSL::SSL OpenSSL::Crypto)
|
|
target_compile_definitions(${TARGET} PRIVATE CPPHTTPLIB_OPENSSL_SUPPORT)
|
|
endif()
|
|
|
|
if (WIN32)
|
|
TARGET_LINK_LIBRARIES(${TARGET} PRIVATE ws2_32)
|
|
endif()
|
|
|
|
target_compile_features(${TARGET} PRIVATE cxx_std_17)
|