Repository navigation

#

distributed-llm

b4rtaz/distributed-llama
b4rtaz / distributed-llama 

Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

distributed-computingllama2大语言模型llm-inference神经网络llmsopen-llmdistributed-llmllama3
C++
2028
14 小时前