trnrt
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
trnrt launched on 30 October 2026. It ranked #23 on Daily Launch on 18 November 2026 with a Launch Score of 58, from 48 points on Show HN and +36 stars on 18 Nov on GitHub. It was new in the ranking that day.
What is trnrt?
TrnRT is an open inference engine for large language models on AWS Trainium. It serves an OpenAI-compatible API from one trn2.48xlarge, runs decode as NKI megakernels (about one kernel per layer half), and keeps a prefix cache across device and host memory. GLM-5.3-Flash is the first supported model; more open models are on the way.
From its README on GitHub
trnrt is a launch on Show HN. It is written in Python and released under the Apache-2.0 license.
In its own words
An open-source LLM inference engine for AWS Trainium
From its Show HN post
Launch timeline
Launch Score, last 7 days
#53 of 226 in the roundup for the week of 16-22 November 2026.