Skip to content

Latest commit

 

History

4 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 

Repository files navigation

Local AI Dockerfiles

Dockerfiles and deployment recipes for local AI inference and supporting services.

Most model-serving images target:

  • NVIDIA RTX PRO 6000 Blackwell GPUs (TP: 1 or TP: 2)
  • AMD EPYC 9355 Turin
  • Up to 768 GB RAM using 12 × 64 GB DDR5-6400

The configurations are hardware-oriented working recipes rather than universal images. Check the documentation accompanying each Dockerfile for compatibility, build instructions, launch parameters and benchmarks.

Models

About

Dockerfiles and deployment recipes for local AI, primarily focused on hybrid GPU+CPU LLM inference

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Contributors