mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-19 17:25:07 +02:00
merge the file structure refactor, testing
This commit is contained in:
Concedo
@@ -1,56 +0,0 @@
|
||||
# dependencies
|
||||
|
||||
find_package(Threads REQUIRED)
|
||||
|
||||
# third-party
|
||||
|
||||
# ...
|
||||
|
||||
# examples
|
||||
|
||||
include_directories(${CMAKE_CURRENT_SOURCE_DIR})
|
||||
|
||||
if (EMSCRIPTEN)
|
||||
else()
|
||||
add_subdirectory(cvector-generator)
|
||||
add_subdirectory(baby-llama)
|
||||
add_subdirectory(batched-bench)
|
||||
add_subdirectory(batched)
|
||||
add_subdirectory(benchmark)
|
||||
add_subdirectory(convert-llama2c-to-ggml)
|
||||
add_subdirectory(embedding)
|
||||
add_subdirectory(eval-callback)
|
||||
add_subdirectory(export-lora)
|
||||
add_subdirectory(finetune)
|
||||
add_subdirectory(gbnf-validator)
|
||||
add_subdirectory(gguf-split)
|
||||
add_subdirectory(gguf)
|
||||
add_subdirectory(gritlm)
|
||||
add_subdirectory(imatrix)
|
||||
add_subdirectory(infill)
|
||||
add_subdirectory(llama-bench)
|
||||
add_subdirectory(llava)
|
||||
add_subdirectory(lookahead)
|
||||
add_subdirectory(lookup)
|
||||
add_subdirectory(main)
|
||||
add_subdirectory(parallel)
|
||||
add_subdirectory(passkey)
|
||||
add_subdirectory(perplexity)
|
||||
add_subdirectory(quantize-stats)
|
||||
add_subdirectory(quantize)
|
||||
add_subdirectory(retrieval)
|
||||
if (LLAMA_RPC)
|
||||
add_subdirectory(rpc)
|
||||
endif()
|
||||
if (LLAMA_BUILD_SERVER)
|
||||
add_subdirectory(server)
|
||||
endif()
|
||||
if (LLAMA_SYCL)
|
||||
add_subdirectory(sycl)
|
||||
endif()
|
||||
add_subdirectory(save-load-state)
|
||||
add_subdirectory(simple)
|
||||
add_subdirectory(speculative)
|
||||
add_subdirectory(tokenize)
|
||||
add_subdirectory(train-text-from-scratch)
|
||||
endif()
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-baby-llama)
|
||||
add_executable(${TARGET} baby-llama.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-batched-bench)
|
||||
add_executable(${TARGET} batched-bench.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-batched)
|
||||
add_executable(${TARGET} batched.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,6 +0,0 @@
|
||||
set(TARGET llama-bench-matmult)
|
||||
add_executable(${TARGET} benchmark-matmult.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE llama build_info ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_include_directories(${TARGET} PRIVATE ../../common)
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-convert-llama2c-to-ggml)
|
||||
add_executable(${TARGET} convert-llama2c-to-ggml.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-cvector-generator)
|
||||
add_executable(${TARGET} cvector-generator.cpp pca.hpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-embedding)
|
||||
add_executable(${TARGET} embedding.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,9 +0,0 @@
|
||||
set(TARGET llama-eval-callback)
|
||||
add_executable(${TARGET} eval-callback.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
|
||||
set(TEST_TARGET test-eval-callback)
|
||||
add_test(NAME ${TEST_TARGET} COMMAND llama-eval-callback --hf-repo ggml-org/models --hf-file tinyllamas/stories260K.gguf --model stories260K.gguf --prompt hello --seed 42 -ngl 0)
|
||||
set_property(TEST ${TEST_TARGET} PROPERTY LABELS eval-callback curl)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-export-lora)
|
||||
add_executable(${TARGET} export-lora.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-finetune)
|
||||
add_executable(${TARGET} finetune.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-gbnf-validator)
|
||||
add_executable(${TARGET} gbnf-validator.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-gguf-split)
|
||||
add_executable(${TARGET} gguf-split.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-gguf)
|
||||
add_executable(${TARGET} gguf.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE ggml ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-gritlm)
|
||||
add_executable(${TARGET} gritlm.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-imatrix)
|
||||
add_executable(${TARGET} imatrix.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -25,7 +25,7 @@ For faster computation, make sure to use GPU offloading via the `-ngl` argument
|
||||
## Example
|
||||
|
||||
```bash
|
||||
LLAMA_CUDA=1 make -j
|
||||
GGML_CUDA=1 make -j
|
||||
|
||||
# generate importance matrix (imatrix.dat)
|
||||
./llama-imatrix -m ggml-model-f16.gguf -f train-data.txt -ngl 99
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-infill)
|
||||
add_executable(${TARGET} infill.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-bench)
|
||||
add_executable(${TARGET} llama-bench.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,55 +0,0 @@
|
||||
|
||||
# For more information about using CMake with Android Studio, read the
|
||||
# documentation: https://d.android.com/studio/projects/add-native-code.html.
|
||||
# For more examples on how to use CMake, see https://github.com/android/ndk-samples.
|
||||
|
||||
# Sets the minimum CMake version required for this project.
|
||||
cmake_minimum_required(VERSION 3.22.1)
|
||||
|
||||
# Declares the project name. The project name can be accessed via ${ PROJECT_NAME},
|
||||
# Since this is the top level CMakeLists.txt, the project name is also accessible
|
||||
# with ${CMAKE_PROJECT_NAME} (both CMake variables are in-sync within the top level
|
||||
# build script scope).
|
||||
project("llama-android")
|
||||
|
||||
## Fetch latest llama.cpp from GitHub
|
||||
#include(FetchContent)
|
||||
#FetchContent_Declare(
|
||||
# llama
|
||||
# GIT_REPOSITORY https://github.com/ggerganov/llama.cpp
|
||||
# GIT_TAG master
|
||||
#)
|
||||
#
|
||||
## Also provides "common"
|
||||
#FetchContent_MakeAvailable(llama)
|
||||
|
||||
# llama.cpp CI uses the code from the current branch
|
||||
# ref: https://github.com/ggerganov/llama.cpp/pull/7341#issuecomment-2117617700
|
||||
add_subdirectory(../../../../../../ build-llama)
|
||||
|
||||
# Creates and names a library, sets it as either STATIC
|
||||
# or SHARED, and provides the relative paths to its source code.
|
||||
# You can define multiple libraries, and CMake builds them for you.
|
||||
# Gradle automatically packages shared libraries with your APK.
|
||||
#
|
||||
# In this top level CMakeLists.txt, ${CMAKE_PROJECT_NAME} is used to define
|
||||
# the target library name; in the sub-module's CMakeLists.txt, ${PROJECT_NAME}
|
||||
# is preferred for the same purpose.
|
||||
#
|
||||
# In order to load a library into your app from Java/Kotlin, you must call
|
||||
# System.loadLibrary() and pass the name of the library defined here;
|
||||
# for GameActivity/NativeActivity derived applications, the same library name must be
|
||||
# used in the AndroidManifest.xml file.
|
||||
add_library(${CMAKE_PROJECT_NAME} SHARED
|
||||
# List C/C++ source files with relative paths to this CMakeLists.txt.
|
||||
llama-android.cpp)
|
||||
|
||||
# Specifies libraries CMake should link to your target library. You
|
||||
# can link libraries from various origins, such as libraries defined in this
|
||||
# build script, prebuilt third-party libraries, or Android system libraries.
|
||||
target_link_libraries(${CMAKE_PROJECT_NAME}
|
||||
# List libraries link to the target library
|
||||
llama
|
||||
common
|
||||
android
|
||||
log)
|
||||
@@ -1,49 +0,0 @@
|
||||
# For more information about using CMake with Android Studio, read the
|
||||
# documentation: https://d.android.com/studio/projects/add-native-code.html.
|
||||
# For more examples on how to use CMake, see https://github.com/android/ndk-samples.
|
||||
|
||||
# Sets the minimum CMake version required for this project.
|
||||
cmake_minimum_required(VERSION 3.22.1)
|
||||
|
||||
# Declares the project name. The project name can be accessed via ${ PROJECT_NAME},
|
||||
# Since this is the top level CMakeLists.txt, the project name is also accessible
|
||||
# with ${CMAKE_PROJECT_NAME} (both CMake variables are in-sync within the top level
|
||||
# build script scope).
|
||||
project("llama-android")
|
||||
|
||||
include(FetchContent)
|
||||
FetchContent_Declare(
|
||||
llama
|
||||
GIT_REPOSITORY https://github.com/ggerganov/llama.cpp
|
||||
GIT_TAG master
|
||||
)
|
||||
|
||||
# Also provides "common"
|
||||
FetchContent_MakeAvailable(llama)
|
||||
|
||||
# Creates and names a library, sets it as either STATIC
|
||||
# or SHARED, and provides the relative paths to its source code.
|
||||
# You can define multiple libraries, and CMake builds them for you.
|
||||
# Gradle automatically packages shared libraries with your APK.
|
||||
#
|
||||
# In this top level CMakeLists.txt, ${CMAKE_PROJECT_NAME} is used to define
|
||||
# the target library name; in the sub-module's CMakeLists.txt, ${PROJECT_NAME}
|
||||
# is preferred for the same purpose.
|
||||
#
|
||||
# In order to load a library into your app from Java/Kotlin, you must call
|
||||
# System.loadLibrary() and pass the name of the library defined here;
|
||||
# for GameActivity/NativeActivity derived applications, the same library name must be
|
||||
# used in the AndroidManifest.xml file.
|
||||
add_library(${CMAKE_PROJECT_NAME} SHARED
|
||||
# List C/C++ source files with relative paths to this CMakeLists.txt.
|
||||
llama-android.cpp)
|
||||
|
||||
# Specifies libraries CMake should link to your target library. You
|
||||
# can link libraries from various origins, such as libraries defined in this
|
||||
# build script, prebuilt third-party libraries, or Android system libraries.
|
||||
target_link_libraries(${CMAKE_PROJECT_NAME}
|
||||
# List libraries link to the target library
|
||||
llama
|
||||
common
|
||||
android
|
||||
log)
|
||||
@@ -1,38 +0,0 @@
|
||||
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_11)
|
||||
|
||||
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 ${CMAKE_THREAD_LIBS_INIT})
|
||||
install(TARGETS llava_shared LIBRARY)
|
||||
endif()
|
||||
|
||||
if (NOT MSVC)
|
||||
target_compile_options(llava PRIVATE -Wno-cast-qual) # stb_image.h
|
||||
endif()
|
||||
|
||||
if(TARGET BUILD_INFO)
|
||||
add_dependencies(llava BUILD_INFO)
|
||||
endif()
|
||||
|
||||
set(TARGET llama-llava-cli)
|
||||
add_executable(${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_11)
|
||||
@@ -194,7 +194,7 @@ llama_print_timings: total time = 44411.01 ms / 377 tokens
|
||||
## Orin compile and run
|
||||
### compile
|
||||
```sh
|
||||
make LLAMA_CUDA=1 CUDA_DOCKER_ARCH=sm_87 LLAMA_CUDA_F16=1 -j 32
|
||||
make GGML_CUDA=1 CUDA_DOCKER_ARCH=sm_87 GGML_CUDA_F16=1 -j 32
|
||||
```
|
||||
### run on Orin
|
||||
### case 1
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-lookahead)
|
||||
add_executable(${TARGET} lookahead.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,23 +0,0 @@
|
||||
set(TARGET llama-lookup)
|
||||
add_executable(${TARGET} lookup.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
|
||||
set(TARGET llama-lookup-create)
|
||||
add_executable(${TARGET} lookup-create.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
|
||||
set(TARGET llama-lookup-merge)
|
||||
add_executable(${TARGET} lookup-merge.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
|
||||
set(TARGET llama-lookup-stats)
|
||||
add_executable(${TARGET} lookup-stats.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,33 +0,0 @@
|
||||
cmake_minimum_required(VERSION 3.12)
|
||||
project("llama-cli-cmake-pkg" C CXX)
|
||||
set(TARGET llama-cli-cmake-pkg)
|
||||
|
||||
find_package(Llama 0.0.1 REQUIRED)
|
||||
|
||||
# Bake common functionality in with target. Because applications
|
||||
# using the relocatable Llama package should be outside of the
|
||||
# source tree, llama-cli-cmake-pkg pretends the dependencies are built-in.
|
||||
set(_common_path "${CMAKE_CURRENT_LIST_DIR}/../../common")
|
||||
add_library(common OBJECT)
|
||||
file(GLOB _common_files
|
||||
"${_common_path}/*.h"
|
||||
"${_common_path}/*.cpp"
|
||||
)
|
||||
target_sources(common PRIVATE ${_common_files})
|
||||
|
||||
# If the common project was part of "llama-cli-cmake-pkg" the transient
|
||||
# defines would automatically be attached. Because the common func-
|
||||
# tionality is separate, but dependent upon the defines, it must be
|
||||
# explicitly extracted from the "llama" target.
|
||||
#
|
||||
get_target_property(_llama_transient_defines llama
|
||||
INTERFACE_COMPILE_DEFINITIONS)
|
||||
|
||||
target_compile_definitions(common PRIVATE "${_llama_transient_defines}")
|
||||
|
||||
add_executable(${TARGET} ${CMAKE_CURRENT_LIST_DIR}/../main/main.cpp)
|
||||
target_include_directories(${TARGET} PRIVATE ${_common_path})
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-cli)
|
||||
add_executable(${TARGET} main.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-parallel)
|
||||
add_executable(${TARGET} parallel.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-passkey)
|
||||
add_executable(${TARGET} passkey.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-perplexity)
|
||||
add_executable(${TARGET} perplexity.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,6 +0,0 @@
|
||||
set(TARGET llama-quantize-stats)
|
||||
add_executable(${TARGET} quantize-stats.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE llama build_info ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_include_directories(${TARGET} PRIVATE ../../common)
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,6 +0,0 @@
|
||||
set(TARGET llama-quantize)
|
||||
add_executable(${TARGET} quantize.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE llama common ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_include_directories(${TARGET} PRIVATE ../../common)
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-retrieval)
|
||||
add_executable(${TARGET} retrieval.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,2 +0,0 @@
|
||||
add_executable(rpc-server rpc-server.cpp)
|
||||
target_link_libraries(rpc-server PRIVATE ggml llama)
|
||||
@@ -29,13 +29,13 @@ You can also run multiple `rpc-server` instances on the same host, each with a d
|
||||
|
||||
## Usage
|
||||
|
||||
On each host, build the corresponding backend with `cmake` and add `-DLLAMA_RPC=ON` to the build options.
|
||||
On each host, build the corresponding backend with `cmake` and add `-DGGML_RPC=ON` to the build options.
|
||||
For example, to build the CUDA backend with RPC support:
|
||||
|
||||
```bash
|
||||
mkdir build-rpc-cuda
|
||||
cd build-rpc-cuda
|
||||
cmake .. -DLLAMA_CUDA=ON -DLLAMA_RPC=ON
|
||||
cmake .. -DGGML_CUDA=ON -DGGML_RPC=ON
|
||||
cmake --build . --config Release
|
||||
```
|
||||
|
||||
@@ -58,12 +58,12 @@ $ CUDA_VISIBLE_DEVICES=0 bin/rpc-server -p 50052
|
||||
This way you can run multiple `rpc-server` instances on the same host, each with a different CUDA device.
|
||||
|
||||
|
||||
On the main host build `llama.cpp` only with `-DLLAMA_RPC=ON`:
|
||||
On the main host build `llama.cpp` only with `-DGGML_RPC=ON`:
|
||||
|
||||
```bash
|
||||
mkdir build-rpc
|
||||
cd build-rpc
|
||||
cmake .. -DLLAMA_RPC=ON
|
||||
cmake .. -DGGML_RPC=ON
|
||||
cmake --build . --config Release
|
||||
```
|
||||
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-save-load-state)
|
||||
add_executable(${TARGET} save-load-state.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,51 +0,0 @@
|
||||
set(TARGET llama-server)
|
||||
option(LLAMA_SERVER_VERBOSE "Build verbose logging option for Server" ON)
|
||||
option(LLAMA_SERVER_SSL "Build SSL support for the server" OFF)
|
||||
include_directories(${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_BINARY_DIR})
|
||||
set(TARGET_SRCS
|
||||
server.cpp
|
||||
utils.hpp
|
||||
httplib.h
|
||||
)
|
||||
set(PUBLIC_ASSETS
|
||||
colorthemes.css
|
||||
style.css
|
||||
theme-beeninorder.css
|
||||
theme-ketivah.css
|
||||
theme-mangotango.css
|
||||
theme-playground.css
|
||||
theme-polarnight.css
|
||||
theme-snowstorm.css
|
||||
index.html
|
||||
index-new.html
|
||||
index.js
|
||||
completion.js
|
||||
system-prompts.js
|
||||
prompt-formats.js
|
||||
json-schema-to-grammar.mjs
|
||||
)
|
||||
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 "${PROJECT_SOURCE_DIR}/scripts/xxd.cmake"
|
||||
)
|
||||
endforeach()
|
||||
add_executable(${TARGET} ${TARGET_SRCS})
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_compile_definitions(${TARGET} PRIVATE
|
||||
SERVER_VERBOSE=$<BOOL:${LLAMA_SERVER_VERBOSE}>
|
||||
)
|
||||
target_link_libraries(${TARGET} PRIVATE common ${CMAKE_THREAD_LIBS_INIT})
|
||||
if (LLAMA_SERVER_SSL)
|
||||
find_package(OpenSSL REQUIRED)
|
||||
target_link_libraries(${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(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-simple)
|
||||
add_executable(${TARGET} simple.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-speculative)
|
||||
add_executable(${TARGET} speculative.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,9 +0,0 @@
|
||||
# MIT license
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: MIT
|
||||
|
||||
set(TARGET llama-ls-sycl-device)
|
||||
add_executable(${TARGET} ls-sycl-device.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_17)
|
||||
@@ -8,10 +8,10 @@ cd build
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
|
||||
#for FP16
|
||||
#cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON # faster for long-prompt inference
|
||||
#cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON # faster for long-prompt inference
|
||||
|
||||
#for FP32
|
||||
cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
|
||||
cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
|
||||
|
||||
#build example/main
|
||||
#cmake --build . --config Release --target main
|
||||
|
||||
@@ -13,10 +13,10 @@ if %errorlevel% neq 0 goto ERROR
|
||||
|
||||
:: for FP16
|
||||
:: faster for long-prompt inference
|
||||
:: cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_CXX_COMPILER=icx -DBUILD_SHARED_LIBS=ON -DCMAKE_BUILD_TYPE=Release -DLLAMA_SYCL_F16=ON
|
||||
:: cmake -G "MinGW Makefiles" .. -DGGML_SYCL=ON -DCMAKE_CXX_COMPILER=icx -DBUILD_SHARED_LIBS=ON -DCMAKE_BUILD_TYPE=Release -DGGML_SYCL_F16=ON
|
||||
|
||||
:: for FP32
|
||||
cmake -G "Ninja" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DBUILD_SHARED_LIBS=ON -DCMAKE_BUILD_TYPE=Release
|
||||
cmake -G "Ninja" .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DBUILD_SHARED_LIBS=ON -DCMAKE_BUILD_TYPE=Release
|
||||
if %errorlevel% neq 0 goto ERROR
|
||||
:: build example/main only
|
||||
:: make main
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-tokenize)
|
||||
add_executable(${TARGET} tokenize.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
@@ -1,5 +0,0 @@
|
||||
set(TARGET llama-train-text-from-scratch)
|
||||
add_executable(${TARGET} train-text-from-scratch.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
Reference in New Issue
Block a user