update 3.8 v2 (#2112)

* update 3.8 v2

* update 3.8

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-02-19 22:03:14 -05:00
committed by GitHub
co-authored by yuzhai
parent e9627ce55b
commit b84e9802d8
166 changed files with 3986 additions and 4037 deletions
+12 -1
View File
@@ -1200,13 +1200,24 @@ public:
GemmGroupedOperation(char const *name = "unknown_gemm"):
GemmOperationBase<Operator_>(name) {
this->description_.gemm_kind = GemmKind::kGrouped;
this->description_.kind = OperationKind::kGroupedGemm;
this->description_.provider = Provider::kCUTLASS;
this->threadblock_count = Operator::sufficient();
this->description_.gemm = GemmOperationBase<Operator_>::description_;
this->description_.gemm.gemm_kind = GemmKind::kGrouped;
this->description_.tile_description = this->description_.gemm.tile_description;
}
/// Returns the description of the GroupedGEMM operation
virtual OperationDescription const & description() const override final {
return description_;
}
private:
int threadblock_count;
GroupedGemmDescription description_;
protected: