← Journal · · Announcement
How to prep Triton: recipes for your inference platform
Hey! My new article is out - this time I put together a small guideline for a repo where I collected useful Triton Inference Server tutorials.
In the repo itself you can find:
- A demo of the inference platform we ship as a private installation at Selectel
- Deploying various model formats in Triton
- Deploying popular LLMs and diffusers (basically foundation models)
- Auto-selection of model format and Triton config
- Simple UI examples for your inference services
Some examples are taken from Triton's official repo (though sometimes their docs can trip you up). So I tried to bring it all into one place.