Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
32 lines
1.3 KiB
Plaintext
32 lines
1.3 KiB
Plaintext
#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
|