{"@context":"https://w3id.org/codemeta/3.0","@type":"SoftwareSourceCode","identifier":"pkg:npm/%40isdk/llama-node","name":"@isdk/llama-node","description":"Low-level Node.js bindings for llama.cpp. Core library for running LLM models locally with native performance and hardware acceleration support.","version":"2.0.3","softwareVersion":"2.0.3","license":"https://spdx.org/licenses/MIT","codeRepository":"https://github.com/isdk/llama-node","url":"https://github.com/isdk/llama-node","keywords":["llama","llama-cpp","llama.cpp","bindings","native","napi","addon","ai","llm","gguf","cmake","cmake-js","prebuilt-binaries","metal","cuda","vulkan","gpu","cpu","inference","tokenize","detokenize","embedding","lora","adapter","context","model","self-hosted","local","offline","typescript","low-level","core","library"],"maintainer":[{"@type":"Person","name":"isdk"}],"author":[{"@type":"Person","name":"isdk"}],"copyrightHolder":[{"@type":"Person","name":"isdk"}],"dateCreated":"2025-12-05","dateModified":"2025-12-12","datePublished":"2025-12-12","copyrightYear":2025,"downloadUrl":"https://registry.npmjs.org/@isdk/llama-node/-/llama-node-2.0.3.tgz","applicationCategory":"npm","runtimePlatform":"npm","sameAs":["https://www.npmjs.com/package/@isdk/llama-node"]}