Commit History

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