How does this fair against other quants without MTP like unsloth?
#4 opened 4 days ago
by
Crigges
Calibration dataset
#3 opened 5 days ago
by
acyildirimer
Heads-up for Ampere users: tq-t4nc recipe + MTP doesn't work with CUDA graphs
3
#2 opened 5 days ago
by
wasifb
[redacted]
1
#1 opened 6 days ago
by
pathosethoslogos