Nehanth/pooled · AI Repo StatsNENehanth/pooled
Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents.
Suy luận & chạy LLM cục bộJavaScript MIT 97tạo 2026-09-01 #browser#distributed-inference#inference#llm#local-llm#peer-to-peer#speculative-decoding#webgpu#webrtc#wgsl