AIJavaScript★ 649⑂ 98 forksMIT
Nehanth/pooled
Browser LLM Device Pool
Run large open‑source LLMs in the browser by linking multiple devices into a peer‑to‑peer compute pool, enabling chat and coding agents without any server.
// KEY FEATURES
- Connects multiple browsers/devices via WebRTC to form a compute pool for LLM inference.
- Splits model layers across peers, letting you run models bigger than one device’s memory.
- Provides a simple API for chat and coding agents to query the pooled model in real time.
#browser#distributed-inference#inference#llm#local-llm#peer-to-peer#speculative-decoding#webgpu#webrtc#wgsl
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram