“Our own chip is going to be an incredible contributor to letting us get very fast inference in the hands of everybody.”
♫
Said on The Every Podcast
“You can set up these disaggregated setups where you're using multiple different types of chips for pre-fill and decode”
Unsupervised Learning with Jacob Effron · Ep 94: Applied Compute CEO on the Limits of RL, the New AI Hyperscaler & Why Post-Training Wins Inference
Play from 30:41
30:41
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
use disaggregated inference setups with separate chips for pre-fill and decode phases
Said nearby on the same subject
“Phase one is like, how can you get sales in? Phase two… build out your car and infrastructure. Phase three… scaling without exploding the engine.”
CM
Clay Mosley
Freelance to Founder ·
“On the government side, almost everybody now is making, you know, in proposal phases, at least document what you used it for, which model you use.”
KP
Karine Pagano Talent Rewire
The Mindtools L&D Podcast ·
“Key takeaway… engage FDA early and often… using pre-IND meetings and the phase two and type C meetings to show… why one trial is sufficient.”
MR
Mark Robbins client
FDA Watch ·
Moments like this, every Monday
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Track a competitor?
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.