Instructions to use VladHong/llama-cpp-K2-FAST2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use VladHong/llama-cpp-K2-FAST2 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: llama cli -hf VladHong/llama-cpp-K2-FAST2
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: llama cli -hf VladHong/llama-cpp-K2-FAST2
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf VladHong/llama-cpp-K2-FAST2 # Run inference directly in the terminal: ./build/bin/llama cli -hf VladHong/llama-cpp-K2-FAST2
Use Docker
docker model run hf.co/VladHong/llama-cpp-K2-FAST2
- Llama new
- LM Studio
- Jan
- Ollama
How to use VladHong/llama-cpp-K2-FAST2 with Ollama:
ollama run hf.co/VladHong/llama-cpp-K2-FAST2
- Unsloth Desktop
- Docker Model Runner
How to use VladHong/llama-cpp-K2-FAST2 with Docker Model Runner:
docker model run hf.co/VladHong/llama-cpp-K2-FAST2
- Lemonade
How to use VladHong/llama-cpp-K2-FAST2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull VladHong/llama-cpp-K2-FAST2
Run and chat with the model
lemonade run user.llama-cpp-K2-FAST2-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download common/CMakeLists.txt from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 4.92 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/common/CMakeLists.txt
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/common/CMakeLists.txt
-
curl -L -o CMakeLists.txt https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/common/CMakeLists.txt
4.92 kB
| find_package(Threads REQUIRED) | |
| llama_add_compile_flags() | |
| # | |
| # llama-common-base | |
| # | |
| # Build info header | |
| if(EXISTS "${PROJECT_SOURCE_DIR}/.git") | |
| set(GIT_DIR "${PROJECT_SOURCE_DIR}/.git") | |
| # Is git submodule | |
| if(NOT IS_DIRECTORY "${GIT_DIR}") | |
| file(READ ${GIT_DIR} REAL_GIT_DIR_LINK) | |
| string(REGEX REPLACE "gitdir: (.*)\n$" "\\1" REAL_GIT_DIR ${REAL_GIT_DIR_LINK}) | |
| string(FIND "${REAL_GIT_DIR}" "/" SLASH_POS) | |
| if (SLASH_POS EQUAL 0) | |
| set(GIT_DIR "${REAL_GIT_DIR}") | |
| else() | |
| set(GIT_DIR "${PROJECT_SOURCE_DIR}/${REAL_GIT_DIR}") | |
| endif() | |
| endif() | |
| if(EXISTS "${GIT_DIR}/index") | |
| # For build-info.cpp below | |
| set_property(DIRECTORY APPEND PROPERTY CMAKE_CONFIGURE_DEPENDS "${GIT_DIR}/index") | |
| else() | |
| message(WARNING "Git index not found in git repository.") | |
| endif() | |
| else() | |
| message(WARNING "Git repository not found; to enable automatic generation of build info, make sure Git is installed and the project is a Git repository.") | |
| endif() | |
| set(TEMPLATE_FILE "${CMAKE_CURRENT_SOURCE_DIR}/build-info.cpp.in") | |
| set(OUTPUT_FILE "${CMAKE_CURRENT_BINARY_DIR}/build-info.cpp") | |
| configure_file(${TEMPLATE_FILE} ${OUTPUT_FILE}) | |
| set(TARGET llama-common-base) | |
| add_library(${TARGET} STATIC ${OUTPUT_FILE}) | |
| target_include_directories(${TARGET} PUBLIC .) | |
| if (BUILD_SHARED_LIBS) | |
| set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON) | |
| endif() | |
| # | |
| # llama-common | |
| # | |
| set(TARGET llama-common) | |
| add_library(${TARGET} | |
| arg.cpp | |
| arg.h | |
| base64.hpp | |
| chat-auto-parser-generator.cpp | |
| chat-auto-parser-helpers.cpp | |
| chat-auto-parser.h | |
| chat-diff-analyzer.cpp | |
| chat-peg-parser.cpp | |
| chat-peg-parser.h | |
| chat.cpp | |
| chat.h | |
| common.cpp | |
| common.h | |
| console.cpp | |
| console.h | |
| debug.cpp | |
| debug.h | |
| download.cpp | |
| download.h | |
| fit.cpp | |
| fit.h | |
| hf-cache.cpp | |
| hf-cache.h | |
| http.h | |
| imatrix-loader.cpp | |
| imatrix-loader.h | |
| json-schema-to-grammar.cpp | |
| json.cpp | |
| json.h | |
| llguidance.cpp | |
| log.cpp | |
| log.h | |
| ngram-cache.cpp | |
| ngram-cache.h | |
| ngram-map.cpp | |
| ngram-map.h | |
| ngram-mod.cpp | |
| ngram-mod.h | |
| peg-parser.cpp | |
| peg-parser.h | |
| preset.cpp | |
| preset.h | |
| reasoning-budget.cpp | |
| reasoning-budget.h | |
| sampling.cpp | |
| sampling.h | |
| speculative.cpp | |
| speculative.h | |
| subproc.cpp | |
| subproc.h | |
| trie.cpp | |
| trie.h | |
| unicode.cpp | |
| unicode.h | |
| jinja/lexer.cpp | |
| jinja/lexer.h | |
| jinja/parser.cpp | |
| jinja/parser.h | |
| jinja/runtime.cpp | |
| jinja/runtime.h | |
| jinja/value.cpp | |
| jinja/value.h | |
| jinja/string.cpp | |
| jinja/string.h | |
| jinja/caps.cpp | |
| jinja/caps.h | |
| ) | |
| set_target_properties(${TARGET} PROPERTIES | |
| VERSION ${LLAMA_VERSION_BASE} | |
| SOVERSION ${LLAMA_VERSION_MAJOR} | |
| MACHO_CURRENT_VERSION 0 # keep macOS linker from seeing oversized version number | |
| ) | |
| target_include_directories(${TARGET} PUBLIC .) | |
| target_link_libraries (${TARGET} PUBLIC vendor::nlohmann vendor::sheredom) | |
| target_compile_features (${TARGET} PUBLIC cxx_std_17) | |
| if (LLAMA_SUBPROCESS) | |
| target_compile_definitions(${TARGET} PUBLIC LLAMA_SUBPROCESS) | |
| endif() | |
| if (BUILD_SHARED_LIBS) | |
| set_target_properties(${TARGET} PROPERTIES POSITION_INDEPENDENT_CODE ON) | |
| # TODO: make fine-grained exports in the future | |
| set_target_properties(${TARGET} PROPERTIES WINDOWS_EXPORT_ALL_SYMBOLS ON) | |
| endif() | |
| target_link_libraries(${TARGET} PUBLIC llama-common-base) | |
| target_link_libraries(${TARGET} PRIVATE cpp-httplib) | |
| if (LLAMA_LLGUIDANCE) | |
| include(ExternalProject) | |
| set(LLGUIDANCE_SRC ${CMAKE_BINARY_DIR}/llguidance/source) | |
| set(LLGUIDANCE_PATH ${LLGUIDANCE_SRC}/target/release) | |
| set(LLGUIDANCE_LIB_NAME "${CMAKE_STATIC_LIBRARY_PREFIX}llguidance${CMAKE_STATIC_LIBRARY_SUFFIX}") | |
| ExternalProject_Add(llguidance_ext | |
| GIT_REPOSITORY https://github.com/guidance-ai/llguidance | |
| # v1.0.1: | |
| GIT_TAG d795912fedc7d393de740177ea9ea761e7905774 | |
| PREFIX ${CMAKE_BINARY_DIR}/llguidance | |
| SOURCE_DIR ${LLGUIDANCE_SRC} | |
| BUILD_IN_SOURCE TRUE | |
| CONFIGURE_COMMAND "" | |
| BUILD_COMMAND cargo build --release --package llguidance | |
| INSTALL_COMMAND "" | |
| BUILD_BYPRODUCTS ${LLGUIDANCE_PATH}/${LLGUIDANCE_LIB_NAME} ${LLGUIDANCE_PATH}/llguidance.h | |
| UPDATE_COMMAND "" | |
| ) | |
| target_compile_definitions(${TARGET} PUBLIC LLAMA_USE_LLGUIDANCE) | |
| add_library(llguidance STATIC IMPORTED) | |
| set_target_properties(llguidance PROPERTIES IMPORTED_LOCATION ${LLGUIDANCE_PATH}/${LLGUIDANCE_LIB_NAME}) | |
| add_dependencies(llguidance llguidance_ext) | |
| target_include_directories(${TARGET} PRIVATE ${LLGUIDANCE_PATH}) | |
| target_link_libraries(${TARGET} PRIVATE llguidance) | |
| if (WIN32) | |
| target_link_libraries(${TARGET} PRIVATE ws2_32 userenv ntdll bcrypt) | |
| endif() | |
| endif() | |
| target_link_libraries(${TARGET} PUBLIC llama Threads::Threads) | |