Re:LLM Training and Inference with Intel Gaudi 2 AI Accelera...
by remexre on Saturday January 06, 2024 @12:59PM
(#38893539)
Kinda funny that instead of NVLink, they're just using (presumably standard) 100GbE as their connector/protocol; wonder if this also lets you wire up larger and more complex topologies of these cards across servers using normal 100GbE switches
[ Parent
| on HN ]
There are no comments on this comment yet.