Sign inSign up

zepai/lark

By zepai

•Updated 5 months ago

A fast, lightweight Rust + CUDA inference server for small language models on a single NVIDIA GPU.

Image
Machine learning & AI
0

137

Tags for zepai/lark

Sort by

Tags cannot be overwritten in this Repository. View in settings

TAG

Last pushed 5 months by danielatzep

docker pull zepai/lark:a2e96df
DigestOS/ARCHCompressed size

a3ea71f839f1

linux/amd64

2.02 GB