[11b/n] Migrate Machete kernels to torch stable ABI (#45304)

Signed-off-by: Chris Leonard <chleonar@redhat.com>
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
This commit is contained in:
Chris Leonard
2026-06-12 10:36:49 +00:00
committed by GitHub
co-authored by Shengqi Chen
parent a37b4a940e
commit a014dddbaa
17 changed files with 341 additions and 323 deletions
@@ -1,31 +0,0 @@
#pragma once
#include "cutlass_extensions/vllm_collective_builder.cuh"
#include "machete_mainloop.cuh"
namespace cutlass::gemm::collective {
using namespace cute;
struct MacheteKernelTag {};
template <class ElementPairA_, class GmemLayoutA_, int AlignmentA,
class ElementPairB_, class GmemLayoutB_, int AlignmentB,
class ElementAccumulator, class TileShape_MNK, class ClusterShape_MNK,
class StageCountType, class KernelScheduleType>
struct VLLMCollectiveBuilder<
MacheteKernelTag, arch::Sm90, arch::OpClassTensorOp, ElementPairA_,
GmemLayoutA_, AlignmentA, ElementPairB_, GmemLayoutB_, AlignmentB,
ElementAccumulator, TileShape_MNK, ClusterShape_MNK, StageCountType,
KernelScheduleType,
cute::enable_if_t<(
cute::is_same_v<KernelScheduleType, KernelTmaWarpSpecialized> ||
cute::is_same_v<KernelScheduleType, KernelTmaWarpSpecializedPingpong> ||
cute::is_same_v<KernelScheduleType,
KernelTmaWarpSpecializedCooperative>)>> {
using CollectiveOp = machete::MacheteCollectiveMma<
ElementPairA_, GmemLayoutA_, AlignmentA, ElementPairB_, GmemLayoutB_,
AlignmentB, ElementAccumulator, TileShape_MNK, ClusterShape_MNK,
StageCountType, KernelScheduleType>;
};
}; // namespace cutlass::gemm::collective