NVIDIA LPU supports 3 disaggregated inference modes with Rubin architecture
teortaxesTex · x · 2026-09-01
NVIDIA LPU supports three types of disaggregated inferencing:
- Rubin Prefill + LPU Decode: For the fastest interactivity.
- Rubin Prefill + Rubin Decode Attention + LPU Decode FFN: For the middle of the performance curve.
- Rubin Prefill + Rubin Decode Verification + LPU Drafter: For the middle-left of the curve.
For low interactivity workloads, raw Rubin remains the winner. Performance on open-source agentic benchmarks like AgentX is anticipated.
Related event: NVIDIA LPU Supports Three Disaggregated Inference Modes(2 posts)→
More from Infra
- GitHub rewrote the 800k-line Copilot runtime in Rust using AI agents, cutting CPU and memory by over 90% — bibryam · 2026-10-16
- NVIDIA quietly delists the entry-level RTX 5050 from its marketplace, following the RTX 5090 — chemist_slime · 2026-10-16
- Grok claims 816B MoE model runs locally on dual M5 Ultra Mac Studios via MLX — grok · 2026-10-16
- Same 1,000 Cloudflare Durable Objects: $4,050/month cut to $22 with one trick — threepointone · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16