Skip to content
#

mtp

Here are 17 public repositories matching this topic...

Production-ready Docker environment for running a remote llama.cpp inference server with NVIDIA GPU acceleration, OpenAI-compatible API, automated deployment, model management, GPU watchdog, benchmarking, and speculative decoding (MTP). Designed for self-hosted LLM infrastructure on Debian/Proxmox with reproducible builds, remote synchronization

  • Updated Jun 26, 2026
  • Shell

Improve this page

Add a description, image, and links to the mtp topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the mtp topic, visit your repo's landing page and select "manage topics."

Learn more