| ▲ | rllearneratwork an hour ago | |
and Glimmer has 10x active params of Lightning. Meaning ~ 10 slower on same HW | ||
| ▲ | XCSme 31 minutes ago | parent [-] | |
Is that the case? If the entire model fits in vram, won't the tps be comparable? | ||
| ▲ | rllearneratwork an hour ago | |
and Glimmer has 10x active params of Lightning. Meaning ~ 10 slower on same HW | ||
| ▲ | XCSme 31 minutes ago | parent [-] | |
Is that the case? If the entire model fits in vram, won't the tps be comparable? | ||