Author | SHA1 Message | Date |
---|---|---|
|
e2f77dbc21 fix quant config | 9 months ago |
|
6ef9a78458 Fix issues with quantization_config == None | 9 months ago |
|
0920b1a415 Fix quantization for inference | 9 months ago |
|
d51d2cce9c adding sdpa for flash attn | 1 year ago |
|
db8af96ff0 update the model load with native flash attn | 1 year ago |
|
4c9cc7d223 Move modules into separate src folder | 1 year ago |