AlpinDale
|
b03b4d4c8c
fix: compute cutlass 3.x epilogues in fp32 instead of 16
|
6 месяцев назад |
AlpinDale
|
5b464d36ea
feat: bias epilogue support for cutlass kernels
|
6 месяцев назад |
AlpinDale
|
7a3e38f79c
fix: cutlass kernel compilation
|
6 месяцев назад |
AlpinDale
|
cd9ed8623b
fix: cuda version check for fp8 support in the cutlass kernels
|
6 месяцев назад |
AlpinDale
|
fad77538de
feat: update cutlass int8 kernel configs for sm90
|
6 месяцев назад |
AlpinDale
|
7e54c3916d
chore: factor out epilogues from cutlass kernels
|
6 месяцев назад |