Y
Hacker News
new
|
ask
|
show
|
jobs
by
syspec
1560 days ago
Wouldn't that much VRAM just be needed for training the model? Not inference?
1 comments
calum-bird
1560 days ago
Haha I wish! That's just loading the weights for inference :)
link
syspec
1559 days ago
I sense a humblebrag
link
calum-bird
1558 days ago
Haha indeed, NLP is fun!
link