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:
@@ -92,6 +92,7 @@ struct UseStagedAccumulation {
|
||||
static bool const value = platform::is_same<Operator, OpMultiplyAddFastF32>::value ||
|
||||
platform::is_same<Operator, OpMultiplyAddComplexFastF32>::value;
|
||||
};
|
||||
|
||||
/////////////////////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
/// Tag indicating the complex multiply-add operation
|
||||
@@ -128,7 +129,7 @@ struct OpClassWmmaTensorOp {};
|
||||
|
||||
/////////////////////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
/// Tag classifing operators as Tensor Core with structure sparse operations.
|
||||
/// Tag classifying operators as Tensor Core with structure sparse operations.
|
||||
struct OpClassSparseTensorOp {};
|
||||
|
||||
/////////////////////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
Reference in New Issue
Block a user