Beyond Matrix Multiplies
20:59–22:21 · 82s
Jensen argues GPUs’ programmability enables algorithmic leaps—like new attention mechanisms or model types—that deliver the 10–100x gains Moore’s Law can’t.
20:59–22:21 · 82s
Jensen argues GPUs’ programmability enables algorithmic leaps—like new attention mechanisms or model types—that deliver the 10–100x gains Moore’s Law can’t.
We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.