AI inference

Explore LLM inference on Kubernetes using Red Hat AI on EKS. Trace requests from the Envoy gateway through the EPP scheduler down to individual vLLM pods.

Optimize LLM deployment with Neural Navigator on Red Hat OpenShift AI, reducing cost overruns and latency spikes.

Confidently deploy LLMs with Red Hat support: Learn how to determine if your model is supported by Red Hat's vLLM community.

See how a team upgraded Red Hat OpenShift AI 3.3.2 three to four times faster with an AI coding assistant, reducing engineering effort by 60%.

Reduce observability costs with Red Hat OpenShift AI summarizer, bridging the interpretation gap for cloud-native architectures.

Explore Kubernetes resources for Red Hat AI Inference on Amazon EKS, enabling intelligent routing for your model serving.

Stop guessing RAG settings. Discover how AutoRAG uses fast evaluation sweeps to optimize chunking and retrieval precision for small LLMs on your data.

Learn how to run isolated Llama 3.1 8B workloads on a single NVIDIA H100 GPU using OpenShift, Kubernetes dynamic resource allocation, and NVIDIA MIG.

Improve model reliability at inference time with its_hub: Learn how to select accurate outputs without retraining.

Optimize GPU efficiency with Red Hat OpenShift AI 3.4's flow control for llm-d, ensuring priority-based request queuing and fairness policies.

Learn how to build a distributed RAG pipeline with Ray Data on OpenShift AI for high-performance parsing, embedding, and writing to a vector database.

Boost AI and analytics workloads with Kove:SDM on Red Hat OpenShift, enabling applications to access memory resources beyond local node limits.

Learn how to build an open cloud native architecture for AI agents. This blueprint explains how to improve workload isolation and implement inference routing.

Learn how to set up local agentic AI computer use. Run quantized models like Qwen 3.6 with Hermes to automate desktop tasks on your own terms today.

Deploy a self-hosted AI coding assistant with vLLM and Red Hat OpenShift AI for privacy and operational independence.

Learn about the llm-d batch gateway, a Kubernetes-native batch inference service that plugs into the same llm-d inference stack managed by Red Hat OpenShift AI.

Explore a demo of serving a multimodal model (Qwen3-Omni) with vLLM-Omni on a single hardware accelerator.

Learn how to implement GPU-as-a-Service on Red Hat OpenShift using Kueue, NVIDIA MIG, and a custom dashboard plug-in for self-service GPU resource booking.

Learn how to optimize deployment of vLLM for various traffic shapes, including high-concurrency chat, long-context RAG, high-throughput batch, and distributed AI-grid.

Learn about the three optimization levers for distributed AI inference: prefill/decode disaggregation, KV cache strategy, and speculative decoding.

Learn how Red Hat's SastAI initiative, in collaboration with NVIDIA, automates false positive identification in static application security testing (SAST) using generative AI. By employing an agentic, multi-stage research workflow, SastAI reduces noise and improves triage efficiency. Discover the pattern harvesting methodology that greatly enhances the SastAI solution, now offering a tighter solution with better knowledge and reasoning.

Learn how to connect the EvalHub runtime to internal or external model servers using service account tokens, API keys, or custom certificates.

Learn how to connect a modern Apache Iceberg lakehouse to LLM-hosted models using nothing but SQL on Red Hat OpenShift AI.

Learn about the five-dimensional design space in modern LLM serving, including tensor, pipeline, expert, data, and context parallelism.

Discover how personal AI notebooks in Red Hat Developer Lightspeed can help developers find specific details in project documents quickly, grounded in context.