Cronologia Commit

Autore SHA1 Messaggio Data
  Matthias Reso e2f77dbc21 fix quant config 9 mesi fa
  Matthias Reso 6ef9a78458 Fix issues with quantization_config == None 9 mesi fa
  Matthias Reso 0920b1a415 Fix quantization for inference 9 mesi fa
  Hamid Shojanazeri d51d2cce9c adding sdpa for flash attn 1 anno fa
  Hamid Shojanazeri db8af96ff0 update the model load with native flash attn 1 anno fa
  Matthias Reso 4c9cc7d223 Move modules into separate src folder 1 anno fa