The story’s score and claims

Comments on No. 94 of 142 · GitHub · edition of Wednesday 18 November 2026

TrnRT – An open-source LLM inference engine for AWS Trainium

Summary

TrnRT is an open-source inference engine for large language models on AWS Trainium2, published by RunAnywhere on GitHub under Apache 2.0. It serves an OpenAI-compatible API from a single trn2.48xlarge, runs decode as fused NKI megakernels, and supports GLM-5.3-Flash with 1M-token context.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules