mdma
Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Hand-written CPU, ROCm, Vulkan, CUDA, Metal and Level Zero kernels, exact memory admission, mTLS gRPC and private federation.
- amd
- apple-silicon
- cuda
- federation
- freebsd
- gguf
- gpu
- grpc
- homelab
- inference
- inference-engine
- level-zero
- llm
- local-llm
- metal
- Stars
- 5
- Forks
- 0
- + today
- +1
- Created
- 22d
Ranking data as of October 13, 2026 (UTC).
Star History
Today, hour by hour
01
Overview
Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Hand-written CPU, ROCm, Vulkan, CUDA, Metal and Level Zero kernels, exact memory admission, mTLS gRPC and private federation. It ranks #2930 on GitTiger, gaining +1 star on October 13, 2026 (UTC).
The project is written in Rust. It was created 22d ago.
Installation
git clone https://github.com/seuros/mdma.git
cd mdma
# see README for setup