Categories / LLM Infrastructure

midagedev

midagedev/bloomery

Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.

Last push 7 hours ago

cudadeepseekggufglminferencellama-cppllmmoeqwenrust

Created

Sep 2026

Total stars

78

Last 7 days

0

Last 30 days

0

Last 12 months

0

README badge

Rusty Stars badge for midagedev/bloomery
[![Rusty Stars](https://rustystars.dev/badge/midagedev/bloomery.svg)](https://rustystars.dev/midagedev/bloomery)