Historique des commits

Auteur SHA1 Message Date
  Matthias Reso e2f77dbc21 fix quant config il y a 10 mois
  Matthias Reso 6ef9a78458 Fix issues with quantization_config == None il y a 10 mois
  Matthias Reso 0920b1a415 Fix quantization for inference il y a 10 mois
  Hamid Shojanazeri d51d2cce9c adding sdpa for flash attn il y a 1 an
  Hamid Shojanazeri db8af96ff0 update the model load with native flash attn il y a 1 an
  Matthias Reso 4c9cc7d223 Move modules into separate src folder il y a 1 an