Flash attention optimization for significant speedup. - old title: Optimization tips to maximize generation speed?
3
#6 opened about 20 hours ago
by 
eepos
ValueError: Buffer too small: needs 56623104 bytes, but only has 35389440.
3
#5 opened 1 day ago
by 
benkhaled
Can someone tell ideogram-ai that their ideomgram-4 nv4 text enconder model is corrupt?
#4 opened 1 day ago
by 
Lowlay
Nvfp4 vs nf4
4
#3 opened 2 days ago
by 
realrebelai
do we need both models
7
#1 opened 2 days ago
by 
ryg81