| ▲ | popalchemist 3 days ago | |
Does 3.6x faster also = 3.6x cheaper? | ||
| ▲ | schopra909 3 days ago | parent [-] | |
Yes, 3.6x cheaper when it comes to training! When it comes to inference it should also be cheaper (since we’ve cut attention sequence length by 4x), but I don’t have a hard number for you how much cheaper for inference | ||