Red Hat AI & CoreWeave: Distributed AI Inference for Hybrid Cloud

Live May 27 at 1:15 PM ET

Running AI inference across hybrid environments — on-prem, multiple clouds, mixed GPUs — is where most enterprise AI strategies start to break down. Join Robert Shaw, Director of Engineering for Inference at Red Hat, and Urvashi Chowdhary, VP of Product Management at CoreWeave, for a live conversation on how Red Hat AI Inference — deployed on CoreWeave Kubernetes Service (CKS) — gives platform teams a consistent way to serve models across hybrid cloud environments.

What we'll cover:
- llm-d — the open source, Kubernetes-native distributed inference framework Red Hat and CoreWeave are building in collaboration with additional AI leaders.
- Why a hardware and model agnostic inference engine is essential as inference demand grows and is multiplied by agentic AI.
- How organizations are serving internal teams and AI agents from shared models and GPU infrastructure — and running those AI initiatives profitably in production.

Whether you're standing up your first production inference platform or scaling to hundreds of models, you'll leave with a clearer picture of what hybrid cloud inference looks like done right.

Resources
🔗 Red Hat AI Inference: red.ht/ai-inference
🔗 Red Hat AI Inference 60-day trial: red.ht/ai-inference-trial
🔗 Deploy Red Hat AI Inference on CoreWeave CKS: docs.coreweave.com/products/cks/tutorials/redhat-inference
🔗 llm-d open source project: llm-d.ai

👍 Like and subscribe for more on enterprise AI infrastructure, open source inference, and Kubernetes at scale.

#HybridCloud #AIInference #llmd #RedHatAI #CoreWeave #Kubernetes #GPUInfrastructure

Видео Red Hat AI & CoreWeave: Distributed AI Inference for Hybrid Cloud канала Red Hat