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 docs/backend/snapdragon/CMakeUserPresets.json from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 4.45 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/docs/backend/snapdragon/CMakeUserPresets.json
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/docs/backend/snapdragon/CMakeUserPresets.json
-
curl -L -o CMakeUserPresets.json https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/docs/backend/snapdragon/CMakeUserPresets.json
4.45 kB
| { | |
| "version": 5, | |
| "configurePresets": [ | |
| { | |
| "name": "arm64-android-snapdragon", | |
| "hidden": true, | |
| "architecture": { "value": "arm64", "strategy": "external" }, | |
| "toolset": { "value": "host=x86_64", "strategy": "external" }, | |
| "cacheVariables": { | |
| "ANDROID_ABI": "arm64-v8a", | |
| "ANDROID_PLATFORM": "android-34", | |
| "CMAKE_TOOLCHAIN_FILE": "$env{ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake", | |
| "CMAKE_C_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -fno-finite-math-only -flto -D_GNU_SOURCE", | |
| "CMAKE_CXX_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -fno-finite-math-only -flto -D_GNU_SOURCE", | |
| "CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG", | |
| "CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG", | |
| "CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g", | |
| "CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g", | |
| "CMAKE_PREFIX_PATH": "$env{OPENCL_SDK_ROOT}", | |
| "HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}", | |
| "HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}", | |
| "PREBUILT_LIB_DIR": "android_aarch64", | |
| "GGML_OPENMP": "OFF", | |
| "GGML_LLAMAFILE": "OFF", | |
| "GGML_OPENCL": "ON", | |
| "GGML_HEXAGON": "ON", | |
| "LLAMA_OPENSSL": "OFF" | |
| } | |
| }, | |
| { | |
| "name": "arm64-windows-snapdragon", | |
| "inherits": [ "base", "arm64-windows-llvm" ], | |
| "cacheVariables": { | |
| "CMAKE_C_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -flto -D_GNU_SOURCE", | |
| "CMAKE_CXX_FLAGS": "-march=armv8.7a+fp16+dotprod+i8mm -fvectorize -ffp-model=fast -flto -D_GNU_SOURCE", | |
| "CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG", | |
| "CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG", | |
| "CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g", | |
| "CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g", | |
| "CMAKE_PREFIX_PATH": "$env{OPENCL_SDK_ROOT}", | |
| "HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}", | |
| "HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}", | |
| "PREBUILT_LIB_DIR": "windows_aarch64", | |
| "GGML_OPENMP": "OFF", | |
| "GGML_LLAMAFILE": "OFF", | |
| "GGML_OPENCL": "ON", | |
| "GGML_HEXAGON": "ON", | |
| "LLAMA_OPENSSL": "OFF" | |
| } | |
| }, | |
| { | |
| "name": "arm64-linux-snapdragon", | |
| "hidden": true, | |
| "architecture": { "value": "arm64", "strategy": "external" }, | |
| "toolset": { "value": "host=x86_64", "strategy": "external" }, | |
| "cacheVariables": { | |
| "CMAKE_TOOLCHAIN_FILE": "cmake/arm64-linux-clang.cmake", | |
| "CMAKE_C_FLAGS": "-march=armv8.2a+fp16+dotprod -fvectorize -fno-finite-math-only -flto -D_GNU_SOURCE", | |
| "CMAKE_CXX_FLAGS": "-march=armv8.2a+fp16+dotprod -fvectorize -fno-finite-math-only -flto -D_GNU_SOURCE", | |
| "CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG", | |
| "CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG", | |
| "CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g", | |
| "CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g", | |
| "CMAKE_PREFIX_PATH": "$env{OPENCL_SDK_ROOT}", | |
| "HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}", | |
| "HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}", | |
| "PREBUILT_LIB_DIR": "linux_aarch64", | |
| "GGML_OPENMP": "OFF", | |
| "GGML_LLAMAFILE": "OFF", | |
| "GGML_OPENCL": "OFF", | |
| "GGML_HEXAGON": "ON", | |
| "LLAMA_OPENSSL": "OFF" | |
| } | |
| }, | |
| { "name": "arm64-android-snapdragon-debug" , "inherits": [ "base", "arm64-android-snapdragon", "debug" ] }, | |
| { "name": "arm64-android-snapdragon-release", "inherits": [ "base", "arm64-android-snapdragon", "release" ] }, | |
| { "name": "arm64-windows-snapdragon-debug" , "inherits": [ "base", "arm64-windows-snapdragon", "debug" ] }, | |
| { "name": "arm64-windows-snapdragon-release", "inherits": [ "base", "arm64-windows-snapdragon", "release" ] }, | |
| { "name": "arm64-linux-snapdragon-debug" , "inherits": [ "base", "arm64-linux-snapdragon", "debug" ] }, | |
| { "name": "arm64-linux-snapdragon-release", "inherits": [ "base", "arm64-linux-snapdragon", "release" ] } | |
| ] | |
| } | |