Nvidia's Cluster Scale Metrics Spark Debate
suchenzang · x · 2026-07-17
This comment discusses how Nvidia's cluster scale is described:
- Clarifying what "scale up domain" means: it could refer to the connection range for a single set of TP/PP model weights, or the maximum size of a super pod that can be linked without performance degradation.
- It also notes a highly unusual unit: 72 of which Nvidia, questioning whether this is a typical server-side Nvidia cluster description.
- The provided numbers show a scale up of 8192 chips versus Nvidia's 72; the maximum scale out size is 500k.
The core takeaway is that different vendors and systems have vastly different metrics and limits regarding large-scale cluster interconnects and scaling.
Related event: Huawei 950 SuperPoD Sparks Debate Over Cluster Scale(9 posts)→
More from Infra
- PoLar: Dynamically Skipping or Looping LLM Layers for Efficient Inference — ttkciar · 2026-07-22
- SK Hynix CEO: Next Year Will Be the Worst Year in Industry's History from Supply Perspective — Beth_Kindig · 2026-07-22
- Tabul AI launches Metal TreeSHAP to speed up Shapley values on Apple silicon — Scobleizer · 2026-07-22
- Tech Giants Are Hiding $1.6T in AI Debt Using Enron's Trick — arto · 2026-07-22
- DeepSeek-V4-Flash tops out at 770 tok/s on one B300 in a vLLM batch test — Moreh · 2026-07-22
- NVIDIA starts shipping 102.4 Tbps Spectrum-6 switches for Vera Rubin AI factories — nvidia · 2026-07-22