The reason is that while a single prediction from a large neural network takes roughly the same amount of compute resource regardless of whether it's for training or end use, the difference is that you need to run squidillions of predictions for training and only one or a handful for end use. So while massively parallel banks of processors (i.e. GPUs, i.e. NVidia) are critical for training models, it makes no discernible difference for using the model after training is complete.
So yes, "we could just use Intel chips to run AI libraries locally".
A bit overpriced ATM, page-33
-
- There are more pages in this discussion • 72 more messages in this thread...
You’re viewing a single post only. To view the entire thread just sign in or Join Now (FREE)
Add DDR (ASX) to my watchlist
 (20min delay)
|
|||||
|
Last
$9.03 |
Change
-0.010(0.11%) |
Mkt cap ! $1.629B | |||
| Open | High | Low | Value | Volume |
| $9.07 | $9.15 | $8.96 | $1.827M | 202.3K |
Buyers (Bids)
| No. | Vol. | Price($) |
|---|---|---|
| 2 | 1400 | $9.00 |
Sellers (Offers)
| Price($) | Vol. | No. |
|---|---|---|
| $9.03 | 662 | 2 |
View Market Depth
| Last trade - 16.10pm 13/09/2024 (20 minute delay) ? |
| DDR (ASX) Chart |