ohdearquant/lattice

Run, quantize, and fine-tune LLMs on Apple Silicon. Pure Rust, no Python, no CUDA, no ONNX

⭐ 40 ⑂ 4 Rust Apache-2.0 · 3 天前推送

apple-silicon embeddings fine-tuning graphdb inference llm local-llm machine-learning quantization retrieval rust

40

Watchers

0

贡献者

0

Commits

0

Releases

141

Open Issues

3 天前

最近推送

原文中文

暂无 README