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 ggml/src/ggml-cpu/cmake/FindSIMD.cmake from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 2.65 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/ggml/src/ggml-cpu/cmake/FindSIMD.cmake
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/ggml/src/ggml-cpu/cmake/FindSIMD.cmake
-
curl -L -o FindSIMD.cmake https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/ggml/src/ggml-cpu/cmake/FindSIMD.cmake
2.65 kB
| include(CheckCSourceRuns) | |
| set(AVX_CODE " | |
| #include <immintrin.h> | |
| int main() | |
| { | |
| __m256 a; | |
| a = _mm256_set1_ps(0); | |
| return 0; | |
| } | |
| ") | |
| set(AVX512_CODE " | |
| #include <immintrin.h> | |
| int main() | |
| { | |
| __m512i a = _mm512_set_epi8(0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0); | |
| __m512i b = a; | |
| __mmask64 equality_mask = _mm512_cmp_epi8_mask(a, b, _MM_CMPINT_EQ); | |
| return 0; | |
| } | |
| ") | |
| set(AVX2_CODE " | |
| #include <immintrin.h> | |
| int main() | |
| { | |
| __m256i a = {0}; | |
| a = _mm256_abs_epi16(a); | |
| __m256i x; | |
| _mm256_extract_epi64(x, 0); // we rely on this in our AVX2 code | |
| return 0; | |
| } | |
| ") | |
| set(FMA_CODE " | |
| #include <immintrin.h> | |
| int main() | |
| { | |
| __m256 acc = _mm256_setzero_ps(); | |
| const __m256 d = _mm256_setzero_ps(); | |
| const __m256 p = _mm256_setzero_ps(); | |
| acc = _mm256_fmadd_ps( d, p, acc ); | |
| return 0; | |
| } | |
| ") | |
| macro(check_sse type flags) | |
| set(__FLAG_I 1) | |
| set(CMAKE_REQUIRED_FLAGS_SAVE ${CMAKE_REQUIRED_FLAGS}) | |
| foreach (__FLAG ${flags}) | |
| if (NOT ${type}_FOUND) | |
| set(CMAKE_REQUIRED_FLAGS ${__FLAG}) | |
| check_c_source_runs("${${type}_CODE}" HAS_${type}_${__FLAG_I}) | |
| if (HAS_${type}_${__FLAG_I}) | |
| set(${type}_FOUND TRUE CACHE BOOL "${type} support") | |
| set(${type}_FLAGS "${__FLAG}" CACHE STRING "${type} flags") | |
| endif() | |
| math(EXPR __FLAG_I "${__FLAG_I}+1") | |
| endif() | |
| endforeach() | |
| set(CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS_SAVE}) | |
| if (NOT ${type}_FOUND) | |
| set(${type}_FOUND FALSE CACHE BOOL "${type} support") | |
| set(${type}_FLAGS "" CACHE STRING "${type} flags") | |
| endif() | |
| mark_as_advanced(${type}_FOUND ${type}_FLAGS) | |
| endmacro() | |
| # flags are for MSVC only! | |
| check_sse("AVX" " ;/arch:AVX") | |
| if (NOT ${AVX_FOUND}) | |
| set(GGML_AVX OFF) | |
| else() | |
| set(GGML_AVX ON) | |
| endif() | |
| check_sse("AVX2" " ;/arch:AVX2") | |
| check_sse("FMA" " ;/arch:AVX2") | |
| if ((NOT ${AVX2_FOUND}) OR (NOT ${FMA_FOUND})) | |
| set(GGML_AVX2 OFF) | |
| else() | |
| set(GGML_AVX2 ON) | |
| endif() | |
| check_sse("AVX512" " ;/arch:AVX512") | |
| if (NOT ${AVX512_FOUND}) | |
| set(GGML_AVX512 OFF) | |
| else() | |
| set(GGML_AVX512 ON) | |
| endif() | |