CUTLASS 3.3.0 (#1167)
* Release 3.3.0 Adds support for mixed precision GEMMs On Hopper and Ampere Adds support for < 16B aligned GEMMs on Hopper Enhancements to EVT Enhancements to Python interface Enhancements to Sub-byte type handling in CuTe Several other bug-fixes and performance improvements. * minor doc update
This commit is contained in:
@@ -489,6 +489,10 @@ struct alignas(1) float_e4m3_t : float8_base<FloatEncoding::E4M3> {
|
||||
explicit float_e4m3_t(int x): float_e4m3_t(float(x)) {
|
||||
}
|
||||
|
||||
CUTLASS_HOST_DEVICE
|
||||
explicit float_e4m3_t(unsigned x): float_e4m3_t(float(x)) {
|
||||
}
|
||||
|
||||
/// E5M2 conversion. Defined after float_e5m2_t is defined.
|
||||
CUTLASS_HOST_DEVICE
|
||||
explicit float_e4m3_t(float_e5m2_t x);
|
||||
@@ -694,6 +698,10 @@ struct alignas(1) float_e5m2_t : float8_base<FloatEncoding::E5M2> {
|
||||
explicit float_e5m2_t(int x): float_e5m2_t(float(x)) {
|
||||
}
|
||||
|
||||
CUTLASS_HOST_DEVICE
|
||||
explicit float_e5m2_t(unsigned x): float_e5m2_t(float(x)) {
|
||||
}
|
||||
|
||||
/// E4M3 conversion
|
||||
CUTLASS_HOST_DEVICE
|
||||
explicit float_e5m2_t(float_e4m3_t x);
|
||||
|
||||
Reference in New Issue
Block a user