NVIDIA LPU supports 3 types of disaggregated inferencing:
1. Rubin Prefill + LPU Decode for the fastest interactivity
2. Rubin Prefill + Rubin Decode Attention + LPU Decode FFN for the middle of the curve
3. Rubin Prefill + Rubin Decode Verification + LPU Drafter for the middle-left of the curve
For low interactivity, raw Rubin still takes the win. Looking forward to seeing Rubin + LPU performance curves on open-source agentic benchmarks like AgentX.
GPTOSS 2T is a proxy model, a made-up model config (layer counts, hidden dims, expert counts, etc.) created by scaling up the GPTOSS 120B architecture so that hardware teams can use it as a stand-in for frontier closed models they can't actually run, like GPT-5 or Gemini. NVIDIA can't benchmark on the real weights.
This is standard practice for hardware architecture & bring-up teams.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
NVIDIA's LPU supports three prefill and decode splits with different interactivity tradeoffs, and raw Rubin still wins at low interactivity. The headline GPTOSS 2T results come from a made-up scaled architecture, not real frontier weights.
postInside Huawei's 1,024-NPU Atlas 950 SuperPoD and its LPO rack fabric
postAMD's inference gap is a software and tooling problem, not a silicon one
articleMost Neoclouds Suck At Security OpenAI vs HuggingFace, Container Escapes,…
