Autor | SHA1 Mensaxe | Data |
---|---|---|
|
e2f77dbc21 fix quant config | hai 9 meses |
|
6ef9a78458 Fix issues with quantization_config == None | hai 9 meses |
|
0920b1a415 Fix quantization for inference | hai 9 meses |
|
d51d2cce9c adding sdpa for flash attn | hai 1 ano |
|
db8af96ff0 update the model load with native flash attn | hai 1 ano |
|
4c9cc7d223 Move modules into separate src folder | hai 1 ano |