GKE launches single-stack IPv6 to keep massive AI/ML deployments from running out of IPs
rseroter · x · 2026-11-20
Google Cloud announced single-stack IPv6 on GKE (preview): nodes and pods run IPv6-only without private IPv4 addresses, available for Cloud TPU v6e and CPU node pools including Axion, with DNS64/NAT64 for IPv4-only endpoints.
The motivation: large AI deployments hit the IP wall before compute or power limits — thousands of accelerator nodes, inference replicas, Ray workers, sidecars and vector databases demand vast address space, and private IPv4 is often already exhausted. IPv6-only clusters avoid conflicts with on-prem networks and peered VPCs and reach Google Cloud APIs natively over IPv6.
More from Infra
- MLX over Vulkan hits 124 tok/s on RTX 5060 Ti, beating llama.cpp CUDA by 25% — SumitGup · 2026-11-22
- Intruder swapped Prime Intellect's hosted DeepSeek for an abliterated copy for 53 hours — mawcopolow · 2026-11-22
- Token economics model projects $1.14T global API spend by 2030, but only 1% of users pay beyond coding — AccBalanced · 2026-11-22
- Zero-degradation Strata tuning: fixing layer_split lifts decode ~10-15% and halves CPU expert misses — PathfinderTactician · 2026-11-22
- llama.cpp Vulkan SCALE fix PR #32735 delivers 2.3-3.2x speedup on Radeon R9700 — pmttyji · 2026-11-22
- $1400 decade-old V100 32GB runs Qwen 27B: Q4_K_M +48% gen speed, Q8_0 +16% prefill — PuzzleheadedArm3732 · 2026-11-22