Nvidia GB200, every mention
2 scenes, the whole family · ← back to Nvidia GB200
tap a year for its mentions
every year anyone Jonathan Frankle 2Sean Lie 1
Verbatim, from the transcripts: the passages where Nvidia GB200 comes up
The Inference Frontier: from 100 to 10,000 tokens per second — Sean Lie, Cerebras CTO
State of the Art: Training 70B LLMs on 10,000 H100 clusters
- ▶ 42:20 Jonathan Frankle You know, for, for both the GH 200 and the GB 200 is this hybrid networking where you'll have blocks of NV link networked chips. 2 times in the scene