Built in C++, distributed-llama is an open-source LLM inference tool maintained by b4rtaz. The repository has collected 3.1k stars and 267 forks; the latest push was in October 2026. Topics include distributed-computing, distributed-llm and llama2.
“Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.”
— b4rtaz, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 3,112 |
| Forks | 267 |
| Language | C++ |
| License | MIT |
| Last updated | |
| Owner | b4rtaz |
| Repository | b4rtaz/distributed-llama |
Tags
distributed-computingdistributed-llmllama2llama3llmllm-inferencellmsneural-network
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.