Home / π§± AI Foundation Stack / π RAG / Retrieval / Vector DB
ohdearquant/lattice
Run, quantize, and fine-tune LLMs on Apple Silicon. Pure Rust, no Python, no CUDA, no ONNX
Commercial license
β Commercial OKApache-2.0
ε―εη¨οΌιεΈΈεͺιδΏηθδ½ζ¬θ²ζ/ζζ¬ζ’ζ¬Ύ
Topics
apple-siliconembeddingsfine-tuninggraphdbinferencellmlocal-llmmachine-learningquantizationretrievalrust
Ad