logoalt Hacker News

girvoyesterday at 10:16 PM1 replyview on HN

> DGX Spark-alike is really just asking for trouble. Prefill kills perf.

You're right that prefill kills perf, but shrug the GB10 has far more compute than it has memory bandwidth, so prefill isn't it's bottleneck.


Replies

htrpyesterday at 11:33 PM

I've seen the same, Sparks are great at non time-sensitive tasks. if you can set up a agentic loop that does not require human intervention, you can design around the memory bandwidth limitations

show 1 reply