{"version":"1.0","workflow_uuid":"b2e0b71d-4b40-45c0-9609-bc5e2abe7c0f","workflow_title":"llama.cpp — Run LLMs Locally in Pure C/C++","install_contract":{"version":"1.0","installReady":false,"title":"llama.cpp — Run LLMs Locally in Pure C/C++","summary":"llama.cpp is a C/C++ LLM inference engine with 100K+ GitHub stars. Runs on CPU, Apple Silicon, NVIDIA, AMD GPUs. 1.5-8 bit quantization, no dependencies, supports 50+ model architectures. MIT licensed","assetType":"Scripts","pageUrl":"https://tokrepo.com/en/workflows/llama-cpp-run-llms-locally-pure-c-c-b2e0b71d","sourceUrl":"https://github.com/ggml-org/llama.cpp","intendedFor":[],"firstActions":[],"agentFirstSteps":[],"targetPaths":[],"verification":[],"startingPoints":[],"example":"","successOutcome":"","boundaries":[],"askUserIf":["the current workspace stack cannot be matched to a safe upstream template","the target path is not the project root, or an existing file should be merged instead of overwritten"]}}