Historia zmian

Autor SHA1 Wiadomość Data
  Tri Dao 27f8f890df [FusedDense] Allocate lt_workspace on input device 1 rok temu
  Tri Dao 88173a1aaf [FusedDense] Support relu, rename FusedDenseGeluDense -> FusedMLP 1 rok temu
  Tri Dao 226a1b721d Implement TensorParallel for FusedDense and FusedDenseGeluDense 2 lat temu
  Tri Dao e68ebbe89a Simplify FusedDense 2 lat temu
  Tri Dao fa6d1ce44f Add fused_dense and dropout_add_layernorm CUDA extensions 2 lat temu