How is the speed? It is very slow with 8 A100s
#8 opened 12 months ago
by
yh-yao

4 Bit hf version here
1
#7 opened 12 months ago
by
srinivasbilla
Trying to load on 8xA10 in 4 bit gives this error
5
#6 opened 12 months ago
by
nbilla
safetensors
#4 opened 12 months ago
by
v2ray

Lets Quantize
8
#1 opened 12 months ago
by
simsim314