🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
132,241 visible repositories in the index
1–4 of 4 · Most stars
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
A new arguably faster implementation of Apache Spark from scratch in Rust
AI based entity resolution, identity resolution, master data management and deduplication at scale for humans and agents