[–] mlsu 2y ago ↗ Why spend almost $1,000 to rent an A10 GPU? You can purchase a used 3090 outright for that much. [–] matroid 2y ago ↗ Two reasons (may not be well thought out or wrong):* Flash Attention, an efficient attention module which significantly speeds up training, only works on Ampere GPUs [1]* Even if I bought a 3090, I would have to get a computer to go with it, along with a PSU and some cooling. Don't know where to start with that.[1] https://github.com/Dao-AILab/flash-attention/issues/190
[–] matroid 2y ago ↗ Two reasons (may not be well thought out or wrong):* Flash Attention, an efficient attention module which significantly speeds up training, only works on Ampere GPUs [1]* Even if I bought a 3090, I would have to get a computer to go with it, along with a PSU and some cooling. Don't know where to start with that.[1] https://github.com/Dao-AILab/flash-attention/issues/190
2 comments
[ 3.9 ms ] story [ 18.3 ms ] thread* Flash Attention, an efficient attention module which significantly speeds up training, only works on Ampere GPUs [1]
* Even if I bought a 3090, I would have to get a computer to go with it, along with a PSU and some cooling. Don't know where to start with that.
[1] https://github.com/Dao-AILab/flash-attention/issues/190