DigestAI news desk

Cut through the AI noise.

Enterprise & Industry4 min read

openKylin unveils KART runtime and agent environment at OSS EU 2026

openKylin, an open‑source Linux community from China, showcased its new KART unified AI runtime and a system‑level agent execution environment during the Open Source Summit Europe 2026 in Prague. Executive Director Min Liu delivered the keynote, while Jianfeng Li presented a lightning talk on an AI‑ready Linux desktop for RISC‑V.

1 source

Key points

  • openKylin introduces KART unified AI runtime and agent execution environment
  • RISC‑V kernel optimizations claim 2–5× speedup in FP32 inference with ONNX Runtime
  • openKylin 3.0 reports 27 million deployments and 2.9 million active users

The company announced openKylin 3.0, which adds an AI Assistant, Global Intelligent Search and Intelligent Space to the desktop. RISC‑V kernel optimizations are claimed to deliver a 2–5× speedup in FP32 inference with ONNX Runtime, and the stack supports vLLM on SpacemiT K3. Distribution options include .deb, Python wheels, Conda and Docker.

The community plans to contribute its RVV kernel work upstream and continue building a runtime foundation, security controls and an open ecosystem for AI hardware, models and applications.

Full story from MarkTechPost · by Michal SutterOpen source ↗

openKylin Outlines Its Vision for Reimagining Linux in the AI Era at Open Source Summit Europe 2026

MarkTechPost · 15 October 2026

Loading the full article…

This text was published by MarkTechPost and written by Michal Sutter. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
openKylinSpacemiTNanyang SingtechDebianUbuntuFedoraKARTvLLMMin LiuJianfeng Li

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Enterprise & Industry

All →

Related stories