Distributed Llama is an open-source project that enables users to connect multiple home devices into a powerful cluster to accelerate Large Language Model (LLM) inference. By leveraging tensor parallelism and high-speed synchronization over Ethernet, it allows for faster performance as more devices are added to the cluster. The system supports various operating systems, including Linux, macOS, and Windows, and is optimized for both ARM and x86_64 AVX2 CPUs.

Features

  • Cluster formation with multiple home devices​
  • Acceleration of LLM inference​
  • Tensor parallelism implementation​
  • High-speed Ethernet synchronization​
  • Support for Linux, macOS, and Windows​
  • Optimization for ARM and x86_64 AVX2 CPUs​
  • Scalability with additional devices​
  • Open-source availability​
  • Active community support​

Project Samples

Project Activity

See All Activity >

Categories

LLM Inference

License

MIT License

Follow Distributed Llama

Distributed Llama Web Site

Other Useful Business Software
Binary Options and Forex Trading Software Icon
Binary Options and Forex Trading Software

For Forex traders (Crypto, Stocks, indices, metals), Binary Option traders

CapitalCore is an online broker offering Forex (CFD) and binary options trading with the highest payouts in the industry. Our platform gives you access to global currency pairs for CFD trading and fast, straightforward binary options. Enjoy quick withdrawals, competitive spreads, and advanced trading tools, all designed to help you succeed. With flexible account options and dedicated support, we’re here to help traders of all levels reach their financial goals.
Learn More
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Distributed Llama!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

C++

Related Categories

C++ LLM Inference Tool

Registered

2025-03-18