Cohere's North Mini Code Megakernel Serving Engine

Cohere · Tuesday, 8 September 2026 at 15:13 (22d ago) · Original article ↗

Cohere presents the first production-ready LLM serving system built around a decode megakernel, achieving 1.58× speedup over vLLM.

You're reading a preview. The full article is published by Cohere on their website.

Read the full story on Cohere

AI Labs

Gemini 4 Argon: our next era of frontier intelligence

Google DeepMind 2h ago

AI Labs

NVIDIA Opens Applications for 2027–2028 Graduate Fellowships With Awards Up to $60,000

Bringing together the world’s brightest minds and the latest accelerated computing technology leads to powerful breakthroughs that help tackle some of the biggest research problems. To foster such innovation, the NVIDIA Graduate Fellowship Program provides grants, mentors and…

NVIDIA Blog 6h ago

AI Labs

Introducing SynthID Bio

Proof of concept for watermarking AI-generated proteins while preserving biological function.

Google DeepMind 7h ago

Cohere's North Mini Code Megakernel Serving Engine

More Official news & blogs from the AI labs

Gemini 4 Argon: our next era of frontier intelligence

NVIDIA Opens Applications for 2027–2028 Graduate Fellowships With Awards Up to $60,000

Introducing SynthID Bio