b4rtaz/distributed-llama · AI Repo StatsB4b4rtaz/distributed-llama
Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
LLM & foundation modelsC++ MIT 260created 2023-12-04 #distributed-computing#distributed-llm#llama2#llama3#llm#llm-inference#llms#neural-network#open-llm