live wire
▸PLATFORM · Quay.io push and pull operations hit intermittent 500 errors during maintenanceRed Hat status▸INTEGRATION · Apache Camel exposes incident and web search as parallel tools for a local agentApache Camel▸AI · Red Hat makes confidential GPU AI GA and previews VM-isolated Agent Sandbox (Aug. 4)Red Hat Blog▸SECURITY · Red Hat fixes Important MariaDB GIS memory-corruption flaw in Hardened ImagesRed Hat Product Security▸SECURITY · Red Hat restores CVE pages after a CWE dependency outage; monitoring continuesRed Hat status▸PLATFORM · Red Hat implements a fix for docs.redhat.com degradation and begins monitoringRed Hat status▸AI · vLLM combines PCP, DCP and host-memory offload to serve 1M-token GLM-5.3 contextsvLLM▸AI · vLLM ships day-zero MiniMax-M3.1-Flash support across NVIDIA and AMD GPUsvLLM▸SECURITY · Red Hat revokes compromised eMudhra certificates across RHEL and OpenShift trust storesRed Hat Product Security▸SECURITY · Red Hat rates PHP2Shell request-handling flaws Important; fixes are rolling outRed Hat Product Security▸AI · IBM maps GPU observability and FinOps controls across OpenShift clustersIBM Community▸IDENTITY · Red Hat shows Data Grid authentication through Keycloak 26 on OpenShiftRed Hat Developer▸AI · Red Hat layers tenant isolation, tool authorization and rate limits onto MCP gatewaysRed Hat Developer▸DATA · Red Hat maps direct LDAP and LDAPS authentication for Data Grid on OpenShiftRed Hat Developer▸PLATFORM · Quay.io push and pull operations hit intermittent 500 errors during maintenanceRed Hat status▸INTEGRATION · Apache Camel exposes incident and web search as parallel tools for a local agentApache Camel▸AI · Red Hat makes confidential GPU AI GA and previews VM-isolated Agent Sandbox (Aug. 4)Red Hat Blog▸SECURITY · Red Hat fixes Important MariaDB GIS memory-corruption flaw in Hardened ImagesRed Hat Product Security▸SECURITY · Red Hat restores CVE pages after a CWE dependency outage; monitoring continuesRed Hat status▸PLATFORM · Red Hat implements a fix for docs.redhat.com degradation and begins monitoringRed Hat status▸AI · vLLM combines PCP, DCP and host-memory offload to serve 1M-token GLM-5.3 contextsvLLM▸AI · vLLM ships day-zero MiniMax-M3.1-Flash support across NVIDIA and AMD GPUsvLLM▸SECURITY · Red Hat revokes compromised eMudhra certificates across RHEL and OpenShift trust storesRed Hat Product Security▸SECURITY · Red Hat rates PHP2Shell request-handling flaws Important; fixes are rolling outRed Hat Product Security▸AI · IBM maps GPU observability and FinOps controls across OpenShift clustersIBM Community▸IDENTITY · Red Hat shows Data Grid authentication through Keycloak 26 on OpenShiftRed Hat Developer▸AI · Red Hat layers tenant isolation, tool authorization and rate limits onto MCP gatewaysRed Hat Developer▸DATA · Red Hat maps direct LDAP and LDAPS authentication for Data Grid on OpenShiftRed Hat Developer
upstreambeat.ai
releaseAI

RHEL AI 3.6 early access moves its base to RHEL 9.8 EUS

The unsupported preview also advances the inference stack, adds a separate vLLM-Omni technology-preview image and narrows the supported upgrade path.

RHEL AI base changes and a separate multimodal preview image.
AI-generated illustration
By The News Desk· Oct 13, 2026the quick take — two AI hosts go live when you do

Red Hat has published the first early-access release of Red Hat Enterprise Linux AI 3.6, moving the product’s operating-system base from RHEL 9.6 to RHEL 9.8 Extended Update Support and refreshing its inference runtime. Red Hat labels the build unsupported and unsuitable for production, making it a test target rather than a deployment recommendation. The 3.6 early-access release notes document the changes and limitations.

A new base and a narrower upgrade gate

The base-image change matters for teams that validate drivers, accelerators and deployment automation against a specific RHEL minor line. The same release notes say an in-place upgrade to 3.6 early access is supported from RHEL AI 3.0 or later, but not directly from RHEL AI 1.5. That leaves older installations needing an intermediate migration plan before they can evaluate the preview.

The bundled inference stack moves to vLLM 0.26.0, while the Red Hat AI Inference component is identified as 3.6.0-fast.1. Those version shifts give platform teams a concrete compatibility target for model, kernel and accelerator testing, but the early-access status means the results should not be treated as a production support commitment.

Multimodal serving arrives as a separate preview

RHEL AI 3.6 also introduces vLLM-Omni as a technology preview. Red Hat packages it in a separate CUDA image based on vLLM-Omni 0.26.1 rather than folding it into the standard inference image. That separation is operationally useful: teams can evaluate multimodal serving without quietly changing the runtime used by existing text-model deployments, while still keeping the preview outside production estates.

Another technology preview exposes Anthropic cache-token information. This can help operators inspect cache behavior and cost-related token accounting in compatible workflows, but it carries the same preview caveat.

Hardware paths remain uneven. Red Hat says the ROCm image does not include the Model Optimization Toolkit, so AMD GPU evaluators should not assume feature parity with the CUDA path when designing 3.6 tests.

What platform teams should do

The practical next step is a disposable validation environment: confirm the RHEL 9.8 EUS base against local security controls, test the supported upgrade route from a 3.x installation, and evaluate the standard and Omni images separately. Production clusters should remain on supported releases until Red Hat moves these capabilities beyond early access.

sources

Filed by The News Desk. Corrections: desk@upstreambeat.ai · Our standards →

comments · 0

    Comments are moderated before they appear. Your email is used once to confirm it is you — never shown, never sold. Corrections and questions get an answer from the desk when we have one.

    more from the desk