Red Hat AI

Learn how to reduce Llama 3.1 8B Instruct model size and improve performance with W8A8 INT8 quantization.

Automate enterprise-wide RAG pipelines with Red Hat OpenShift AI's AutoRAG, speeding up AI optimization for your business.

Manage AI infrastructure costs and governance with Red Hat AI 3.4's Model-as-a-Service.

Learn how to install and configure OpenCode, an open source AI coding assistant, for local development with Ollama, OpenVINO, or Red Hat AI.

Improve large language model inference speed with Speculators 0.6.0's FastMTP-style fine-tuning.

Cut Llama 3.1 8B VRAM by 46% without losing accuracy. Master the mechanics of INT8 W8A8 quantization, SmoothQuant, and GPTQ using llm-compressor.

Learn how to configure admission fair sharing in Red Hat build of Kueue 1.4 on OpenShift to prevent job starvation and balance shared resources cluster quotas.

Learn how P-EAGLE in Speculators v0.6.0 uses parallel drafting to reduce LLM latency. Train and deploy custom draft models with this step-by-step guide.

Learn how to reduce LLM memory footprint and costs with our guide on quantization schemes for inference engines

Headed to Devoxx Belgium 2026? Visit the Red Hat Developer booth on-site to speak to our expert technologists.

Learn how to fine-tune large language models on Red Hat OpenShift AI with Ray and Training Hub for optimized SQL generation using the LoRA algorithm.

Learn how to optimize self-hosted LLM cost per token. Cut GPU spending and maximize real-world throughput with autoscaling, right-sizing, and vLLM tuning.

Learn how to “crash test” an AI model before it hits production by probing it the way real users and attackers will. You’ll see what can go wrong when a model ships without safety training, then walk through running NVIDIA’s open source Garak scanner locally against GPT-2. The episode breaks down how Garark works and the next steps for production readiness.

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.

Battle-test your AI agents before production. Discover how MiDojo's open source framework red-teams tool calls for real-world security and utility.

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.

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

Learn behavioral testing for agents, catching non-deterministic failures with golden queries and YAML files.

Consider a scenario where a zero-day vulnerability in a supply chain component allows an attacker to execute code inside one of your pods. Even if your network policies successfully block them from pivoting to other namespaces or exfiltrating data, they are still inside the pod, where attempts to run reconnaissance scripts, inject payloads, or execute shell commands, can take place.

The moment the attacker tries to execute a dangerous command or exhibit suspicious behavior, ACS detects the anomaly. Because these policies are set to termination mode within the ZTVP, ACS doesn't just send an alert, it immediately kills the rogue pod.
This is the ultimate synergy of defense in depth: Network policies block the attacker's escape routes, and active runtime monitoring eliminates the threat entirely. Even if a configuration was missed, the risk of a successful, prolonged attack drops effectively to zero.

Boost AI coding agent performance with AGENTS.md and Agent Skills. Learn how to standardize project context, structure tasks, and share skills across teams.

Learn how PyTorch's Inductor compiler and vertical fusion optimize GPU code for faster neural network layers

Headed to JavaZone 2026? Visit the Red Hat Developer booth on-site to speak to our expert technologists.

Learn how to parse SEC filings into JSON objects matching a given schema with agentic-graphrag-finance.

Agentic AI is cool, but how can we make it actually do things for us? Welcome to the world of Computer Use, where your model can take action for you on your desktop, and perform actions like typing, clicking, and more.

In this demo, we run an open source, natively multimodal model (Qwen3.6, 35B sparse MoE) locally on Mac using MLX, then connect it to Hermes, an AI agent with built-in guardrails for computer use. Watch it move a chess piece, apply a Photo Booth filter, and read a graph straight out of a research paper, all by seeing the screen and clicking, typing, and navigating like a human would. Everything runs on your own hardware through an OpenAI-compatible endpoint, so nothing you see or do ever leaves your machine.

#ComputerUse #AIAgents #RedHatAI #LocalLLM #PrivateAI #OpenSourceAI