From the NVIDIA edition of September 15, 2026
AI Enterprise EOL notices add immediate and January 2027 NIM migration deadlines
NVIDIA · AI platform vendor lifecycle policy · Global
- Publisher
- NVIDIA AI Enterprise End of Life Notices
- Original publication
- NVIDIA AI Enterprise Lifecycle Policy – EOL Notices (retrieved 2026-09-15)
- Source retrieved
- 2026-09-15
What happened
EOL notices list immediate End of Support for NIM Llama-3.1-70b-instruct (migrate to Llama-3.3-70b-instruct or Multi-LLM NIM), Morpheus, and Optimized TensorFlow 2, plus January 2027 deprecations for several PB6 model-specific NIMs (including Nemotron 3 Nano and Llama-3.3-Nemotron-Super-49B-v1.5) and removal of older GPUs from Infra 8.x with Infra 4.10 LTSB already EOL July 2026.
Why it matters
SLED estates still on Llama-3.1-70B NIM or older Infra LTSB branches face active support cliffs; education/gov platforms should schedule migrations before PB6 sunset.
Evidence and measured results
Opened EOL page tables Active Notices for deprecated and immediate End of Support components, with migration paths and action dates including Immediate and January 2027 (PB6).
Limitations and uncertainty
Vendor policy page; local entitlement and branch mapping still required. Some deprecation dates are future (Jan 2027).
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-09-15; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Customers may be unknowingly running EOS NIM models or dead Infra LTSB branches.
- Stakeholders
- platform owner
- procurement
- CISO
- Discovery questions
- Which Production Branch and Infra branch are in production?
- Any Llama-3.1-70B NIM still serving?
- What is the PB6 exit plan?
- Value hypothesis
- Lifecycle-aligned architectures reduce unplanned outages and audit findings.
- Potential engagement
- Lifecycle exposure assessment and migration proposal.
- Unsupported claims
- Deprecated means still fully supported
- Infra 4.10 remains a viable long-term path
Pre-sales engineering
Role takeaway
- Fit
- Fit as mandatory constraint set for supported NVIDIA AI Enterprise estates.
- Architecture and integration
- Replace EOS NIMs; validate successors; align Infra branch to supported GPUs.
- Prerequisites
- Software bill of materials
- Entitlement mapping
- Eval of successor models
- Constraints
- Immediate EOS items
- PB6 sunset Jan 2027
- GPU removals on Infra 8.x
- Security
- Unsupported software lacks CVE fixes—treat as elevated risk.
- Proof of value
- EOS components removed or firewalled
- Successor eval passed
- Branch document updated
Delivery
Role takeaway
- Work
- Migration project for EOS/deprecated components with scheduled cutovers.
- Dependencies
- app teams
- platform
- security
- Ownership
- Platform owns branch policy; apps own model cutovers.
- Skills and adoption
- Teams need lifecycle literacy in runbooks.
- Governance checkpoints
- SBOM review
- Security exception expiry
- Cutover rehearsal
- Acceptance criteria
- No immediate EOS in prod
- Jan 2027 plan dated
- Docs updated
- Risks
- Silent continued use of EOS
- Late PB6 crunch
- GPU support surprises
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
Prefer model-free NIM or currently supported model-specific NIMs; plan GPU refreshes off Infra 4.10; avoid new Morpheus/TF2 dependencies.
Governance
Who approves, reviews and stays accountable for outcomes?
Lifecycle review belongs in quarterly governance; unsupported components are procurement and audit findings.
Security and privacy
What data, permissions and controls need testing?
End of Support means no further CVE patches for listed artifacts—continuing use increases vulnerability exposure.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Forced migrations can disrupt teaching/research assistants unless successor models are validated early.
Procurement
What should contracts, pricing and exit terms secure?
Write lifecycle compliance and migration assistance into renewals; disallow new deploy on immediate EOS components.
Operating model
Which teams own the service once it runs?
Add EOL monitoring to AI platform operations equal to CVE scanning.
Publication history
- 2026-09-15NVIDIA · Issue 1010 resources
Stable resource ID: nvidia-aie-eol-notices-nim-migration-windows-2026