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-sycl/diag.cpp 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-sycl/diag.cpp
- Command line
-
hf download hf://VladHong/llama-cpp-K2-FAST2/ggml/src/ggml-sycl/diag.cpp
-
curl -L -o diag.cpp https://huggingface.co/VladHong/llama-cpp-K2-FAST2/resolve/main/ggml/src/ggml-sycl/diag.cpp
2.19 kB
| template <typename T> | |
| static void diag_kernel(T * __restrict__ dst, const T * __restrict__ src, | |
| const int64_t ne0, const int64_t ne1, | |
| const int64_t ne2, const int64_t ne3, | |
| const int64_t total_elements, | |
| const sycl::nd_item<1> & item) { | |
| const int64_t i = item.get_global_id(0); | |
| if (i >= total_elements) { | |
| return; | |
| } | |
| const int64_t i0 = i % ne0; | |
| const int64_t i1 = (i / ne0) % ne1; | |
| const int64_t i2 = (i / (ne0 * ne1)) % ne2; | |
| const int64_t i3 = i / (ne0 * ne1 * ne2); | |
| const int64_t dst_idx = ((i3 * ne2 + i2) * ne1 + i1) * ne0 + i0; | |
| if (i0 == i1) { | |
| const int64_t batch_idx = i3 * ne2 + i2; | |
| dst[dst_idx] = src[batch_idx * ne0 + i0]; | |
| } else { | |
| dst[dst_idx] = T(0); | |
| } | |
| (void)ne3; | |
| } | |
| inline void ggml_sycl_op_diag(ggml_backend_sycl_context & ctx, ggml_tensor * dst) { | |
| const ggml_tensor * src0 = dst->src[0]; | |
| GGML_ASSERT(ggml_is_contiguous(dst)); | |
| GGML_ASSERT(ggml_is_contiguous(src0)); | |
| GGML_ASSERT(src0->ne[1] == 1); | |
| dpct::queue_ptr stream = ctx.stream(); | |
| SYCL_CHECK(ggml_sycl_set_device(ctx.device)); | |
| const void * src0_d = src0->data; | |
| void * dst_d = dst->data; | |
| const int64_t ne0 = dst->ne[0]; | |
| const int64_t ne1 = dst->ne[1]; | |
| const int64_t ne2 = dst->ne[2]; | |
| const int64_t ne3 = dst->ne[3]; | |
| const int64_t n_elems = ggml_nelements(dst); | |
| const int64_t num_blocks = (n_elems + SYCL_DIAG_BLOCK_SIZE - 1) / SYCL_DIAG_BLOCK_SIZE; | |
| GGML_ASSERT(dst->type == GGML_TYPE_F32); | |
| stream->parallel_for( | |
| sycl::nd_range<1>(num_blocks * SYCL_DIAG_BLOCK_SIZE, SYCL_DIAG_BLOCK_SIZE), | |
| [=](sycl::nd_item<1> item) { | |
| diag_kernel(static_cast<float *>(dst_d), | |
| static_cast<const float *>(src0_d), | |
| ne0, ne1, ne2, ne3, n_elems, item); | |
| }); | |
| } | |
| void ggml_sycl_diag(ggml_backend_sycl_context & ctx, ggml_tensor * dst) { | |
| scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/1); | |
| ggml_sycl_op_diag(ctx, dst); | |
| } | |