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/virtgpu-utils.h from VladHong/llama-cpp-K2-FAST2: direct link, hf CLI and curl.
- Browser
- Download file 2.19 kB
-
https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/ggml/src/ggml-virtgpu/virtgpu-utils.h
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/ggml/src/ggml-virtgpu/virtgpu-utils.h
-
curl -L -o virtgpu-utils.h https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/ggml/src/ggml-virtgpu/virtgpu-utils.h
2.19 kB
| /** Checks is a value is a power of two. Does not handle zero. */ | |
| /** Checks is a value is a power of two. Zero handled. */ | |
| /** Align a value to a power of two */ | |
| static inline bool util_is_power_of_two_nonzero64(uint64_t v) { | |
| return IS_POT_NONZERO(v); | |
| } | |
| static inline uint64_t align64(uint64_t value, uint64_t alignment) { | |
| assert(util_is_power_of_two_nonzero64(alignment)); | |
| return ALIGN_POT(value, alignment); | |
| } | |
| struct list_head { | |
| list_head * prev; | |
| list_head * next; | |
| }; | |
| struct util_sparse_array { | |
| size_t elem_size; | |
| unsigned node_size_log2; | |
| uintptr_t root; | |
| }; | |
| void * util_sparse_array_get(util_sparse_array * arr, uint64_t idx); | |
| void util_sparse_array_init(util_sparse_array * arr, size_t elem_size, size_t node_size); | |
| inline void os_time_sleep(int64_t usecs) { | |
| timespec time; | |
| time.tv_sec = usecs / 1000000; | |
| time.tv_nsec = (usecs % 1000000) * 1000; | |
| while (clock_nanosleep(CLOCK_MONOTONIC, 0, &time, &time) == EINTR) | |
| ; | |
| } | |
| struct timer_data { | |
| long long start; | |
| long long total; | |
| long long count; | |
| }; | |
| static inline void start_timer(timer_data * timer) { | |
| timespec ts; | |
| clock_gettime(CLOCK_MONOTONIC, &ts); | |
| timer->start = (long long) ts.tv_sec * 1000000000LL + ts.tv_nsec; | |
| } | |
| // returns the duration in ns | |
| static inline long long stop_timer(timer_data * timer) { | |
| timespec ts; | |
| clock_gettime(CLOCK_MONOTONIC, &ts); | |
| long long timer_end = (long long) ts.tv_sec * 1000000000LL + ts.tv_nsec; | |
| long long duration = (timer_end - timer->start); | |
| timer->total += duration; | |
| timer->count += 1; | |
| return duration; | |
| } | |