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-virtgpu/backend/backend-dispatched.cpp from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 1.57 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/ggml/src/ggml-virtgpu/backend/backend-dispatched.cpp
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/ggml/src/ggml-virtgpu/backend/backend-dispatched.cpp
-
curl -L -o backend-dispatched.cpp https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/ggml/src/ggml-virtgpu/backend/backend-dispatched.cpp
1.57 kB
| ggml_backend_reg_t reg = NULL; | |
| ggml_backend_dev_t dev = NULL; | |
| ggml_backend_t bck = NULL; | |
| uint64_t timer_start = 0; | |
| uint64_t timer_total = 0; | |
| uint64_t timer_count = 0; | |
| uint32_t backend_dispatch_initialize(void * ggml_backend_reg_fct_p) { | |
| if (reg != NULL) { | |
| GGML_LOG_WARN(GGML_VIRTGPU_BCK "%s: already initialized\n", __func__); | |
| return APIR_BACKEND_INITIALIZE_ALREADY_INITED; | |
| } | |
| ggml_backend_reg_t (*ggml_backend_reg_fct)(void) = (ggml_backend_reg_t (*)()) ggml_backend_reg_fct_p; | |
| reg = ggml_backend_reg_fct(); | |
| if (reg == NULL) { | |
| GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: backend registration failed\n", __func__); | |
| return APIR_BACKEND_INITIALIZE_BACKEND_REG_FAILED; | |
| } | |
| size_t device_count = reg->iface.get_device_count(reg); | |
| if (!device_count) { | |
| GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: no device found\n", __func__); | |
| return APIR_BACKEND_INITIALIZE_NO_DEVICE; | |
| } | |
| dev = reg->iface.get_device(reg, 0); | |
| if (!dev) { | |
| GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: failed to get device\n", __func__); | |
| return APIR_BACKEND_INITIALIZE_NO_DEVICE; | |
| } | |
| bck = dev->iface.init_backend(dev, NULL); | |
| if (!bck) { | |
| GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: backend initialization failed\n", __func__); | |
| return APIR_BACKEND_INITIALIZE_BACKEND_INIT_FAILED; | |
| } | |
| return APIR_BACKEND_INITIALIZE_SUCCESS; | |
| } | |