Guide llama.cpp builds, installs, and runtime configuration from official docs.
npx skills add https://github.com/wenerme/ai --skill llamacpp-docs
Please help me install this Agent Skill. Skill: llamacpp-docs Source: https://github.com/wenerme/ai/tree/main/skills/llamacpp-docs Command: npx skills add https://github.com/wenerme/ai --skill llamacpp-docs
This Skill helps you quickly find correct, authoritative guidance for building, installing, and using llama.cpp without hunting through scattered sources.
Use the llamacpp-docs skill to look up how to build and run llama.cpp with the CUDA backend in Docker.
High-intent search queries and answers about installing and using this skill.
Building llama.cpp with the CUDA backend requires specific CMake flags during source compilation. The Skill provides structured, topic-indexed guidance for enabling GPU backends like CUDA, ensuring you reference the correct official documentation steps.
Loading GGUF models in llama.cpp involves specific runtime configuration commands. This Skill surfaces official documentation to guide you through the process, ensuring correct model loading without manual navigation through scattered sources.
Yes, llama.cpp supports advanced features like function calling, tool use, and speculative decoding. This Skill references official documentation to explain these runtime features, helping you implement them correctly in your applications.
Compiling llama.cpp for RISC-V, s390x, or Android is supported through architecture-specific builds. The Skill provides curated official documentation to guide you through the necessary CMake and installation steps for these environments.
You can configure multiple GPU backends for llama.cpp including CUDA, Metal, Vulkan, OpenCL, SYCL, and CANN. The Skill delivers official documentation references to help you set up and enable the correct backend for your hardware.
Using curated official documentation for llama.cpp installation ensures you get authoritative, reliable build and configuration steps. This Skill surfaces topic-indexed answers directly from official sources, preventing errors from outdated or scattered third-party tutorials.
Binh230199Review and generate modern target-based CMake for embedded C and C++ build systems.
NeuroSkill-comRun a local llama.cpp server for OpenAI-compatible chat and GGUF model management.
arsityQuantize machine learning models to GGUF for CPU and Apple Silicon deployment.
hochoa13Generate type-safe JSON, XML, or code output using Pydantic models.
