Red Hat has released Red Hat AI 3.5 with updates including new observability dashboards offering “comprehensive metrics to gain real-time insight into inference health, GPU utilization, and AI model performance.”
With Red Hat AI 3.5, organizations can also “verify models before deployment through EvalHub, enabling risk-focused safety benchmarking and the creation of regulatory compliance certifications,” the announcement states.
Key features include:
- Verifiable pre-deployment model evaluation for safety and compliance
- Shared GPU control for multi-tenant inference
- Agent APIs and gateway security with a unified open source interface
- Enterprise data grounding and efficient reasoning
- Built-in observability with agentic tracing and performance dashboards
- Pre-built agent templates for faster development
“The conversation has moved from getting AI into production to running it at scale as trusted enterprise infrastructure, which requires safety evidence, governed agents, cost attribution and multi-tenancy,” says Joe Fernandes, vice president and general manager, AI Business Unit, Red Hat.
Learn more at Red Hat.
