HOT RADAR
opensourceHEAT 13.3°

AI CURATED HOT STORY · 11/18/2026

Open-Source TrnRT Brings LLM Inference to AWS Trainium Chips

1 reports archived1 independent sourcesupdated 11/18/2026, 00:01:04
Synthesis & Latest Updates
1 Sources Cross-Validated

runanywhere.ai released TrnRT, an open-source inference engine that serves an OpenAI-compatible API from a single trn2.48xlarge instance on AWS Trainium, using NKI layer megakernels for decode, 1M-token sparse/linear attention, and a radix-tree prefix cache spanning device and host memory. GLM-5.3-Flash is the first supported model, with AgentX coding benchmark results published alongside.

LATEST/runanywhere.ai released TrnRT, an open-source inference engine that serves an OpenAI-compatible API from a single trn2.48xlarge instance on AWS Trainium, using NKI layer megakernels for decode, 1M-token sparse/linear attention, and a radix-tree prefix cache spanning device and host memory. GLM-5.3-Flash is the first supported model, with AgentX coding benchmark results published alongside.

Hourly heat curve

6 fully observed hours
Now
13.3
Peak
15.202:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first