do we need new quants for vllm 10.1?
#4 opened 15 days ago
by
Fernanda24
Does it possible to create a version without MTP layer to save some VRAM
👍
1
1
#3 opened 21 days ago
by
adonishong
how did you make it
#2 opened 22 days ago
by
ehartford

How many GPU Memory AWQ need?
5
#1 opened 23 days ago
by
hermitg