Hugging Face's logo

Second State

company
https://github.com/second-state/LlamaEdge
secondstateinc
second-state
Request to join this org

AI & ML interests

Run open source LLMs across CPU and GPU without changing the binary in Rust and Wasm locally!

Organization Card
Community About org cards

Run Open source LLMs and create OpenAI-compatible API services for the Llama2 series of LLMs locally With LlamaEdge!

Give it a try

Run a single command in your command line terminal.

bash <(curl -sSfL 'https://raw.githubusercontent.com/LlamaEdge/LlamaEdge/main/run-llm.sh') --interactive

Follow the on-screen instructions to install the WasmEdge Runtime and download your favorite open-source LLM. Then, choose whether you want to chat with the model via the CLI or via a web UI.

See it in action | GitHub | Docs

Why?

LlamaEdge, powered by Rust and WasmEdge, provides a strong alternative to Python in AI inference.

  • Lightweight. The total runtime size is 30MB.
  • Fast. Full native speed on GPUs.
  • Portable. Single cross-platform binary on different CPUs, GPUs, and OSes.
  • Secure. Sandboxed and isolated execution on untrusted devices.
  • Container-ready. Supported in Docker, containerd, Podman, and Kubernetes.

Learn more

Please visit the LlamaEdge project to learn more.

Collections 7

models 189

datasets

None public yet