@ReflectionAI @huggingface Our engineers made it even faster while you were reading! Throughput is already up from 70K → ~90K since we posted.
Reflection AI reports throughput rising from 70K to about 90K
AISummary
Reflection AI says its engineers made the system faster, with throughput rising from 70K to about 90K since its earlier post. The post, from NVIDIA AI, replies to Reflection AI and Hugging Face and does not name the system or the unit of throughput.
Post on XView on X
Source: NVIDIA AI · x.comPublished · added here