[Kernel] Refactor Cutlass c3x (#10049)

Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

csrc/cutlass_extensions/epilogue/scaled_mm_epilogues_c2x.hpp

@@ -1,3 +1,5 @@
+#pragma once
+
 #include "cutlass_extensions/epilogue/broadcast_load_epilogue_c2x.hpp"
 
 /*

csrc/cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp

@@ -1,3 +1,5 @@
+#pragma once
+
 #include "cutlass_extensions/epilogue/broadcast_load_epilogue_c3x.hpp"
 
 /*

csrc/quantization/cutlass_w8a8/scaled_mm_c2x.cuh

@@ -28,9 +28,9 @@
 using namespace cute;
 
 /*
-   Epilogue functions can be defined to post-process the output before it is
+   Epilogues defined in,
-   written to GPU memory.
+   csrc/cutlass_extensions/epilogue/scaled_mm_epilogues_c2x.hpp
-   Epilogues must contain a public type named EVTCompute of type Sm80EVT,
+   must contain a public type named EVTCompute of type Sm80EVT,
    as well as a static prepare_args function that constructs an
    EVTCompute::Arguments struct.
 */

csrc/quantization/cutlass_w8a8/scaled_mm_c3x.cu

@@ -1,385 +1,18 @@
-// clang-format will break include orders
-// clang-format off
 #include <cudaTypedefs.h>
 
 #if defined CUDA_VERSION && CUDA_VERSION >= 12000
 
-#include <torch/all.h>
+  #include "scaled_mm_c3x_sm90_fp8_dispatch.cuh"
+  #include "scaled_mm_c3x_sm90_int8_dispatch.cuh"
 
-#include <ATen/cuda/CUDAContext.h>
+  #include "cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp"
-
-#include <iostream>
-#include <sstream>
-#include <vector>
-
-#include "cutlass/cutlass.h"
-
-#include "cute/tensor.hpp"
-#include "cute/atom/mma_atom.hpp"
-#include "cutlass/numeric_types.h"
-
-#include "cutlass/gemm/device/gemm_universal_adapter.h"
-#include "cutlass/gemm/kernel/gemm_universal.hpp"
-#include "cutlass/epilogue/collective/collective_builder.hpp"
-#include "cutlass/gemm/collective/collective_builder.hpp"
-
-#include "cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp"
-#include "core/math.hpp"
-#include "cutlass_extensions/common.hpp"
-// clang-format on
-
-using namespace cute;
 using namespace vllm;
 
 /*
    This file defines quantized GEMM operations using the CUTLASS 3.x API, for
    NVIDIA GPUs with sm90a (Hopper) or later.
-
-   Epilogue functions can be defined to post-process the output before it is
-   written to GPU memory.
-   Epilogues must contain a public type named EVTCompute of type Sm90EVT,
-   as well as a static prepare_args function that constructs an
-   EVTCompute::Arguments struct.
 */
 
-namespace {
-
-// A wrapper for the GEMM kernel that is used to guard against compilation on
-// architectures that will never use the kernel. The purpose of this is to
-// reduce the size of the compiled binary.
-// __CUDA_ARCH__ is not defined in host code, so this lets us smuggle the ifdef
-// into code that will be executed on the device where it is defined.
-template <typename Kernel>
-struct enable_sm90_or_later : Kernel {
-  template <typename... Args>
-  CUTLASS_DEVICE void operator()(Args&&... args) {
-  #if defined __CUDA_ARCH__ && __CUDA_ARCH__ >= 900
-    Kernel::operator()(std::forward<Args>(args)...);
-  #endif
-  }
-};
-template <typename ElementAB_, typename ElementD_,
-          template <typename, typename, typename> typename Epilogue_,
-          typename TileShape, typename ClusterShape, typename KernelSchedule,
-          typename EpilogueSchedule>
-struct cutlass_3x_gemm {
-  using ElementAB = ElementAB_;
-  using ElementD = ElementD_;
-  using ElementAcc =
-      typename std::conditional<std::is_same_v<ElementAB, int8_t>, int32_t,
-                                float>::type;
-
-  using EpilogueDescriptor =
-      cutlass::epilogue::collective::detail::EpilogueDescriptor<
-          TileShape, cutlass::epilogue::collective::EpilogueTileAuto, ElementD,
-          ElementD, EpilogueSchedule>;
-
-  using Epilogue = Epilogue_<ElementAcc, ElementD, EpilogueDescriptor>;
-
-  using StrideD = Stride<int64_t, Int<1>, Int<0>>;
-  using ElementC = void;
-  using StrideC = StrideD;
-
-  using EVTCompute = typename Epilogue::EVTCompute;
-
-  using CollectiveEpilogue =
-      typename cutlass::epilogue::collective::CollectiveBuilder<
-          cutlass::arch::Sm90, cutlass::arch::OpClassTensorOp, TileShape,
-          ClusterShape, cutlass::epilogue::collective::EpilogueTileAuto,
-          ElementAcc, float, ElementC, StrideC, 4, ElementD, StrideD, 4,
-          EpilogueSchedule, EVTCompute>::CollectiveOp;
-
-  static constexpr size_t CEStorageSize =
-      sizeof(typename CollectiveEpilogue::SharedStorage);
-  using Stages = typename cutlass::gemm::collective::StageCountAutoCarveout<
-      static_cast<int>(CEStorageSize)>;
-
-  // clang-format off
-  using CollectiveMainloop =
-      typename cutlass::gemm::collective::CollectiveBuilder<
-          cutlass::arch::Sm90, cutlass::arch::OpClassTensorOp, 
-          ElementAB, cutlass::layout::RowMajor, 16, 
-          ElementAB, cutlass::layout::ColumnMajor, 16, 
-          ElementAcc, TileShape, ClusterShape,
-          Stages,
-          KernelSchedule>::CollectiveOp;
-  // clang-format on
-
-  using KernelType = enable_sm90_or_later<cutlass::gemm::kernel::GemmUniversal<
-      cute::Shape<int, int, int, int>, CollectiveMainloop, CollectiveEpilogue,
-      cutlass::gemm::PersistentScheduler>>;
-
-  struct GemmKernel : public KernelType {};
-};
-
-template <typename Gemm, typename... EpilogueArgs>
-void cutlass_gemm_caller(torch::Tensor& out, torch::Tensor const& a,
-                         torch::Tensor const& b,
-                         EpilogueArgs&&... epilogue_params) {
-  using ElementAB = typename Gemm::ElementAB;
-  using ElementD = typename Gemm::ElementD;
-
-  int32_t m = a.size(0);
-  int32_t n = b.size(1);
-  int32_t k = a.size(1);
-
-  int64_t lda = a.stride(0);
-  int64_t ldb = b.stride(1);
-  int64_t ldc = out.stride(0);
-
-  using StrideA = Stride<int64_t, Int<1>, int64_t>;
-  using StrideB = Stride<int64_t, Int<1>, int64_t>;
-  using StrideC = typename Gemm::StrideC;
-
-  StrideA a_stride{lda, Int<1>{}, 0};
-  StrideB b_stride{ldb, Int<1>{}, 0};
-  StrideC c_stride{ldc, Int<1>{}, Int<0>{}};
-
-  using GemmKernel = typename Gemm::GemmKernel;
-  typename GemmKernel::ProblemShape prob_shape{m, n, k, 1};
-
-  auto a_ptr = static_cast<ElementAB*>(a.data_ptr());
-  auto b_ptr = static_cast<ElementAB*>(b.data_ptr());
-  typename GemmKernel::MainloopArguments mainloop_args{a_ptr, a_stride, b_ptr,
-                                                       b_stride};
-
-  auto c_ptr = static_cast<ElementD*>(out.data_ptr());
-  typename GemmKernel::EpilogueArguments epilogue_args{
-      Gemm::Epilogue::prepare_args(
-          std::forward<EpilogueArgs>(epilogue_params)...),
-      c_ptr, c_stride, c_ptr, c_stride};
-
-  typename GemmKernel::Arguments args{cutlass::gemm::GemmUniversalMode::kGemm,
-                                      prob_shape, mainloop_args, epilogue_args};
-
-  // Launch the CUTLASS GEMM kernel.
-  using GemmOp = cutlass::gemm::device::GemmUniversalAdapter<GemmKernel>;
-  GemmOp gemm_op;
-  CUTLASS_CHECK(gemm_op.can_implement(args));
-
-  size_t workspace_size = gemm_op.get_workspace_size(args);
-  auto const workspace_options =
-      torch::TensorOptions().dtype(torch::kUInt8).device(a.device());
-  auto workspace = torch::empty(workspace_size, workspace_options);
-
-  auto stream = at::cuda::getCurrentCUDAStream(a.get_device());
-
-  cutlass::Status status = gemm_op.run(args, workspace.data_ptr(), stream);
-  CUTLASS_CHECK(status);
-}
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue>
-struct sm90_fp8_config_default {
-  // M in (128, inf)
-  static_assert(std::is_same<InType, cutlass::float_e4m3_t>());
-  using KernelSchedule =
-      cutlass::gemm::KernelTmaWarpSpecializedPingpongFP8FastAccum;
-  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
-  using TileShape = Shape<_128, _128, _128>;
-  using ClusterShape = Shape<_2, _1, _1>;
-  using Cutlass3xGemm =
-      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
-                      KernelSchedule, EpilogueSchedule>;
-};
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue>
-struct sm90_fp8_config_M128 {
-  // M in (64, 128]
-  static_assert(std::is_same<InType, cutlass::float_e4m3_t>());
-  using KernelSchedule =
-      cutlass::gemm::KernelTmaWarpSpecializedPingpongFP8FastAccum;
-  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
-  using TileShape = Shape<_64, _128, _128>;
-  using ClusterShape = Shape<_2, _1, _1>;
-  using Cutlass3xGemm =
-      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
-                      KernelSchedule, EpilogueSchedule>;
-};
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue>
-struct sm90_fp8_config_M64 {
-  // M in [1, 64]
-  static_assert(std::is_same<InType, cutlass::float_e4m3_t>());
-  using KernelSchedule =
-      cutlass::gemm::KernelTmaWarpSpecializedPingpongFP8FastAccum;
-  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
-  using TileShape = Shape<_64, _64, _128>;
-  using ClusterShape = Shape<_1, _8, _1>;
-
-  using Cutlass3xGemm =
-      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
-                      KernelSchedule, EpilogueSchedule>;
-};
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue>
-struct sm90_int8_config_default {
-  // For M > 128 and any N
-  static_assert(std::is_same<InType, int8_t>());
-  using KernelSchedule =
-      typename cutlass::gemm::KernelTmaWarpSpecializedPingpong;
-  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
-  using TileShape = Shape<_128, _128, _128>;
-  using ClusterShape = Shape<_2, _1, _1>;
-  using Cutlass3xGemm =
-      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
-                      KernelSchedule, EpilogueSchedule>;
-};
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue>
-struct sm90_int8_config_M128 {
-  // For M in (64, 128] and any N
-  static_assert(std::is_same<InType, int8_t>());
-  using KernelSchedule =
-      typename cutlass::gemm::KernelTmaWarpSpecializedPingpong;
-  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
-  using TileShape = Shape<_64, _128, _128>;
-  using ClusterShape = Shape<_2, _1, _1>;
-  using Cutlass3xGemm =
-      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
-                      KernelSchedule, EpilogueSchedule>;
-};
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue>
-struct sm90_int8_config_M64 {
-  // For M in (32, 64] and any N
-  static_assert(std::is_same<InType, int8_t>());
-  using KernelSchedule = typename cutlass::gemm::KernelTmaWarpSpecialized;
-  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
-  using TileShape = Shape<_64, _64, _256>;
-  using ClusterShape = Shape<_1, _1, _1>;
-  using Cutlass3xGemm =
-      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
-                      KernelSchedule, EpilogueSchedule>;
-};
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue>
-struct sm90_int8_config_M32_NBig {
-  // For M in [1, 32] and N >= 8192
-  static_assert(std::is_same<InType, int8_t>());
-  using KernelSchedule = typename cutlass::gemm::KernelTmaWarpSpecialized;
-  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
-  using TileShape = Shape<_64, _128, _256>;
-  using ClusterShape = Shape<_1, _4, _1>;
-  using Cutlass3xGemm =
-      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
-                      KernelSchedule, EpilogueSchedule>;
-};
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue>
-struct sm90_int8_config_M32_NSmall {
-  // For M in [1, 32] and N < 8192
-  static_assert(std::is_same<InType, int8_t>());
-  using KernelSchedule = typename cutlass::gemm::KernelTmaWarpSpecialized;
-  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
-  using TileShape = Shape<_64, _64, _256>;
-  using ClusterShape = Shape<_1, _8, _1>;
-  using Cutlass3xGemm =
-      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
-                      KernelSchedule, EpilogueSchedule>;
-};
-
-}  // namespace
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue,
-          typename... EpilogueArgs>
-void cutlass_gemm_sm90_fp8_dispatch(torch::Tensor& out, torch::Tensor const& a,
-                                    torch::Tensor const& b,
-                                    EpilogueArgs&&... args) {
-  static_assert(std::is_same<InType, cutlass::float_e4m3_t>());
-  TORCH_CHECK(a.dtype() == torch::kFloat8_e4m3fn);
-  TORCH_CHECK(b.dtype() == torch::kFloat8_e4m3fn);
-
-  using Cutlass3xGemmDefault =
-      typename sm90_fp8_config_default<InType, OutType,
-                                       Epilogue>::Cutlass3xGemm;
-  using Cutlass3xGemmM64 =
-      typename sm90_fp8_config_M64<InType, OutType, Epilogue>::Cutlass3xGemm;
-  using Cutlass3xGemmM128 =
-      typename sm90_fp8_config_M128<InType, OutType, Epilogue>::Cutlass3xGemm;
-
-  uint32_t const m = a.size(0);
-  uint32_t const mp2 =
-      std::max(static_cast<uint32_t>(64), next_pow_2(m));  // next power of 2
-
-  if (mp2 <= 64) {
-    // m in [1, 64]
-    return cutlass_gemm_caller<Cutlass3xGemmM64>(
-        out, a, b, std::forward<EpilogueArgs>(args)...);
-  } else if (mp2 <= 128) {
-    // m in (64, 128]
-    return cutlass_gemm_caller<Cutlass3xGemmM128>(
-        out, a, b, std::forward<EpilogueArgs>(args)...);
-  } else {
-    // m in (128, inf)
-    return cutlass_gemm_caller<Cutlass3xGemmDefault>(
-        out, a, b, std::forward<EpilogueArgs>(args)...);
-  }
-}
-
-template <typename InType, typename OutType,
-          template <typename, typename, typename> typename Epilogue,
-          typename... EpilogueArgs>
-void cutlass_gemm_sm90_int8_dispatch(torch::Tensor& out, torch::Tensor const& a,
-                                     torch::Tensor const& b,
-                                     EpilogueArgs&&... args) {
-  static_assert(std::is_same<InType, int8_t>());
-  TORCH_CHECK(a.dtype() == torch::kInt8);
-  TORCH_CHECK(b.dtype() == torch::kInt8);
-
-  using Cutlass3xGemmDefault =
-      typename sm90_int8_config_default<InType, OutType,
-                                        Epilogue>::Cutlass3xGemm;
-  using Cutlass3xGemmM128 =
-      typename sm90_int8_config_M128<InType, OutType, Epilogue>::Cutlass3xGemm;
-  using Cutlass3xGemmM64 =
-      typename sm90_int8_config_M64<InType, OutType, Epilogue>::Cutlass3xGemm;
-  using Cutlass3xGemmM32NBig =
-      typename sm90_int8_config_M32_NBig<InType, OutType,
-                                         Epilogue>::Cutlass3xGemm;
-  using Cutlass3xGemmM32NSmall =
-      typename sm90_int8_config_M32_NSmall<InType, OutType,
-                                           Epilogue>::Cutlass3xGemm;
-
-  uint32_t const n = out.size(1);
-  bool const is_small_n = n < 8192;
-
-  uint32_t const m = a.size(0);
-  uint32_t const mp2 =
-      std::max(static_cast<uint32_t>(32), next_pow_2(m));  // next power of 2
-
-  if (mp2 <= 32) {
-    // m in [1, 32]
-    if (is_small_n) {
-      return cutlass_gemm_caller<Cutlass3xGemmM32NSmall>(
-          out, a, b, std::forward<EpilogueArgs>(args)...);
-    } else {
-      return cutlass_gemm_caller<Cutlass3xGemmM32NBig>(
-          out, a, b, std::forward<EpilogueArgs>(args)...);
-    }
-  } else if (mp2 <= 64) {
-    // m in (32, 64]
-    return cutlass_gemm_caller<Cutlass3xGemmM64>(
-        out, a, b, std::forward<EpilogueArgs>(args)...);
-  } else if (mp2 <= 128) {
-    // m in (64, 128]
-    return cutlass_gemm_caller<Cutlass3xGemmM128>(
-        out, a, b, std::forward<EpilogueArgs>(args)...);
-  } else {
-    // m in (128, inf)
-    return cutlass_gemm_caller<Cutlass3xGemmDefault>(
-        out, a, b, std::forward<EpilogueArgs>(args)...);
-  }
-}
-
 template <template <typename, typename, typename> typename Epilogue,
           typename... EpilogueArgs>
 void cutlass_scaled_mm_sm90_epilogue(torch::Tensor& out, torch::Tensor const& a,

csrc/quantization/cutlass_w8a8/scaled_mm_c3x.cuh

@@ -0,0 +1,160 @@
+#pragma once
+
+// clang-format will break include orders
+// clang-format off
+#include <torch/all.h>
+
+#include <ATen/cuda/CUDAContext.h>
+
+#include "cutlass/cutlass.h"
+
+#include "cute/tensor.hpp"
+#include "cute/atom/mma_atom.hpp"
+#include "cutlass/numeric_types.h"
+
+#include "cutlass/gemm/device/gemm_universal_adapter.h"
+#include "cutlass/gemm/kernel/gemm_universal.hpp"
+#include "cutlass/epilogue/collective/collective_builder.hpp"
+#include "cutlass/gemm/collective/collective_builder.hpp"
+
+#include "core/math.hpp"
+#include "cutlass_extensions/common.hpp"
+// clang-format on
+
+/*
+  Epilogues defined in,
+  csrc/cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp,
+  must contain a public type named EVTCompute of type Sm90EVT, as well as a
+  static prepare_args function that constructs an EVTCompute::Arguments struct.
+*/
+
+using namespace cute;
+
+namespace vllm {
+
+// A wrapper for the GEMM kernel that is used to guard against compilation on
+// architectures that will never use the kernel. The purpose of this is to
+// reduce the size of the compiled binary.
+// __CUDA_ARCH__ is not defined in host code, so this lets us smuggle the ifdef
+// into code that will be executed on the device where it is defined.
+template <typename Kernel>
+struct enable_sm90_or_later : Kernel {
+  template <typename... Args>
+  CUTLASS_DEVICE void operator()(Args&&... args) {
+#if defined __CUDA_ARCH__ && __CUDA_ARCH__ >= 900
+    Kernel::operator()(std::forward<Args>(args)...);
+#endif
+  }
+};
+
+template <typename ElementAB_, typename ElementD_,
+          template <typename, typename, typename> typename Epilogue_,
+          typename TileShape, typename ClusterShape, typename KernelSchedule,
+          typename EpilogueSchedule>
+struct cutlass_3x_gemm {
+  using ElementAB = ElementAB_;
+  using ElementD = ElementD_;
+  using ElementAcc =
+      typename std::conditional<std::is_same_v<ElementAB, int8_t>, int32_t,
+                                float>::type;
+
+  using EpilogueDescriptor =
+      cutlass::epilogue::collective::detail::EpilogueDescriptor<
+          TileShape, cutlass::epilogue::collective::EpilogueTileAuto, ElementD,
+          ElementD, EpilogueSchedule>;
+
+  using Epilogue = Epilogue_<ElementAcc, ElementD, EpilogueDescriptor>;
+
+  using StrideD = Stride<int64_t, Int<1>, Int<0>>;
+  using ElementC = void;
+  using StrideC = StrideD;
+
+  using EVTCompute = typename Epilogue::EVTCompute;
+
+  using CollectiveEpilogue =
+      typename cutlass::epilogue::collective::CollectiveBuilder<
+          cutlass::arch::Sm90, cutlass::arch::OpClassTensorOp, TileShape,
+          ClusterShape, cutlass::epilogue::collective::EpilogueTileAuto,
+          ElementAcc, float, ElementC, StrideC, 4, ElementD, StrideD, 4,
+          EpilogueSchedule, EVTCompute>::CollectiveOp;
+
+  static constexpr size_t CEStorageSize =
+      sizeof(typename CollectiveEpilogue::SharedStorage);
+  using Stages = typename cutlass::gemm::collective::StageCountAutoCarveout<
+      static_cast<int>(CEStorageSize)>;
+
+  // clang-format off
+  using CollectiveMainloop =
+      typename cutlass::gemm::collective::CollectiveBuilder<
+          cutlass::arch::Sm90, cutlass::arch::OpClassTensorOp, 
+          ElementAB, cutlass::layout::RowMajor, 16, 
+          ElementAB, cutlass::layout::ColumnMajor, 16, 
+          ElementAcc, TileShape, ClusterShape,
+          Stages,
+          KernelSchedule>::CollectiveOp;
+  // clang-format on
+
+  using KernelType = enable_sm90_or_later<cutlass::gemm::kernel::GemmUniversal<
+      cute::Shape<int, int, int, int>, CollectiveMainloop, CollectiveEpilogue,
+      cutlass::gemm::PersistentScheduler>>;
+
+  struct GemmKernel : public KernelType {};
+};
+
+template <typename Gemm, typename... EpilogueArgs>
+void cutlass_gemm_caller(torch::Tensor& out, torch::Tensor const& a,
+                         torch::Tensor const& b,
+                         EpilogueArgs&&... epilogue_params) {
+  using ElementAB = typename Gemm::ElementAB;
+  using ElementD = typename Gemm::ElementD;
+
+  int32_t m = a.size(0);
+  int32_t n = b.size(1);
+  int32_t k = a.size(1);
+
+  int64_t lda = a.stride(0);
+  int64_t ldb = b.stride(1);
+  int64_t ldc = out.stride(0);
+
+  using StrideA = Stride<int64_t, Int<1>, int64_t>;
+  using StrideB = Stride<int64_t, Int<1>, int64_t>;
+  using StrideC = typename Gemm::StrideC;
+
+  StrideA a_stride{lda, Int<1>{}, 0};
+  StrideB b_stride{ldb, Int<1>{}, 0};
+  StrideC c_stride{ldc, Int<1>{}, Int<0>{}};
+
+  using GemmKernel = typename Gemm::GemmKernel;
+  typename GemmKernel::ProblemShape prob_shape{m, n, k, 1};
+
+  auto a_ptr = static_cast<ElementAB*>(a.data_ptr());
+  auto b_ptr = static_cast<ElementAB*>(b.data_ptr());
+  typename GemmKernel::MainloopArguments mainloop_args{a_ptr, a_stride, b_ptr,
+                                                       b_stride};
+
+  auto c_ptr = static_cast<ElementD*>(out.data_ptr());
+  typename GemmKernel::EpilogueArguments epilogue_args{
+      Gemm::Epilogue::prepare_args(
+          std::forward<EpilogueArgs>(epilogue_params)...),
+      c_ptr, c_stride, c_ptr, c_stride};
+
+  typename GemmKernel::Arguments args{cutlass::gemm::GemmUniversalMode::kGemm,
+                                      prob_shape, mainloop_args, epilogue_args};
+
+  // Launch the CUTLASS GEMM kernel.
+  using GemmOp = cutlass::gemm::device::GemmUniversalAdapter<GemmKernel>;
+  GemmOp gemm_op;
+  CUTLASS_CHECK(gemm_op.can_implement(args));
+
+  size_t workspace_size = gemm_op.get_workspace_size(args);
+  auto const workspace_options =
+      torch::TensorOptions().dtype(torch::kUInt8).device(a.device());
+  auto workspace = torch::empty(workspace_size, workspace_options);
+
+  auto stream = at::cuda::getCurrentCUDAStream(a.get_device());
+
+  cutlass::Status status = gemm_op.run(args, workspace.data_ptr(), stream);
+  CUTLASS_CHECK(status);
+}
+
+}  // namespace vllm

csrc/quantization/cutlass_w8a8/scaled_mm_c3x_sm90_fp8_dispatch.cuh

@@ -0,0 +1,96 @@
+#pragma once
+
+#include "scaled_mm_c3x.cuh"
+
+/**
+ * This file defines Gemm kernel configurations for SM90 (fp8) based on the Gemm
+ * shape.
+ */
+
+namespace vllm {
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue>
+struct sm90_fp8_config_default {
+  // M in (128, inf)
+  static_assert(std::is_same<InType, cutlass::float_e4m3_t>());
+  using KernelSchedule =
+      cutlass::gemm::KernelTmaWarpSpecializedPingpongFP8FastAccum;
+  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
+  using TileShape = Shape<_128, _128, _128>;
+  using ClusterShape = Shape<_2, _1, _1>;
+  using Cutlass3xGemm =
+      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
+                      KernelSchedule, EpilogueSchedule>;
+};
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue>
+struct sm90_fp8_config_M128 {
+  // M in (64, 128]
+  static_assert(std::is_same<InType, cutlass::float_e4m3_t>());
+  using KernelSchedule =
+      cutlass::gemm::KernelTmaWarpSpecializedPingpongFP8FastAccum;
+  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
+  using TileShape = Shape<_64, _128, _128>;
+  using ClusterShape = Shape<_2, _1, _1>;
+  using Cutlass3xGemm =
+      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
+                      KernelSchedule, EpilogueSchedule>;
+};
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue>
+struct sm90_fp8_config_M64 {
+  // M in [1, 64]
+  static_assert(std::is_same<InType, cutlass::float_e4m3_t>());
+  using KernelSchedule =
+      cutlass::gemm::KernelTmaWarpSpecializedPingpongFP8FastAccum;
+  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
+  using TileShape = Shape<_64, _64, _128>;
+  using ClusterShape = Shape<_1, _8, _1>;
+
+  using Cutlass3xGemm =
+      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
+                      KernelSchedule, EpilogueSchedule>;
+};
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue,
+          typename... EpilogueArgs>
+inline void cutlass_gemm_sm90_fp8_dispatch(torch::Tensor& out,
+                                           torch::Tensor const& a,
+                                           torch::Tensor const& b,
+                                           EpilogueArgs&&... args) {
+  static_assert(std::is_same<InType, cutlass::float_e4m3_t>());
+  TORCH_CHECK(a.dtype() == torch::kFloat8_e4m3fn);
+  TORCH_CHECK(b.dtype() == torch::kFloat8_e4m3fn);
+
+  using Cutlass3xGemmDefault =
+      typename sm90_fp8_config_default<InType, OutType,
+                                       Epilogue>::Cutlass3xGemm;
+  using Cutlass3xGemmM64 =
+      typename sm90_fp8_config_M64<InType, OutType, Epilogue>::Cutlass3xGemm;
+  using Cutlass3xGemmM128 =
+      typename sm90_fp8_config_M128<InType, OutType, Epilogue>::Cutlass3xGemm;
+
+  uint32_t const m = a.size(0);
+  uint32_t const mp2 =
+      std::max(static_cast<uint32_t>(64), next_pow_2(m));  // next power of 2
+
+  if (mp2 <= 64) {
+    // m in [1, 64]
+    return cutlass_gemm_caller<Cutlass3xGemmM64>(
+        out, a, b, std::forward<EpilogueArgs>(args)...);
+  } else if (mp2 <= 128) {
+    // m in (64, 128]
+    return cutlass_gemm_caller<Cutlass3xGemmM128>(
+        out, a, b, std::forward<EpilogueArgs>(args)...);
+  } else {
+    // m in (128, inf)
+    return cutlass_gemm_caller<Cutlass3xGemmDefault>(
+        out, a, b, std::forward<EpilogueArgs>(args)...);
+  }
+}
+
+}  // namespace vllm

csrc/quantization/cutlass_w8a8/scaled_mm_c3x_sm90_int8_dispatch.cuh

@@ -0,0 +1,140 @@
+#pragma once
+
+#include "scaled_mm_c3x.cuh"
+
+/**
+ * This file defines Gemm kernel configurations for SM90 (int8) based on the
+ * Gemm shape.
+ */
+
+namespace vllm {
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue>
+struct sm90_int8_config_default {
+  // For M > 128 and any N
+  static_assert(std::is_same<InType, int8_t>());
+  using KernelSchedule =
+      typename cutlass::gemm::KernelTmaWarpSpecializedPingpong;
+  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
+  using TileShape = Shape<_128, _128, _128>;
+  using ClusterShape = Shape<_2, _1, _1>;
+  using Cutlass3xGemm =
+      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
+                      KernelSchedule, EpilogueSchedule>;
+};
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue>
+struct sm90_int8_config_M128 {
+  // For M in (64, 128] and any N
+  static_assert(std::is_same<InType, int8_t>());
+  using KernelSchedule =
+      typename cutlass::gemm::KernelTmaWarpSpecializedPingpong;
+  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
+  using TileShape = Shape<_64, _128, _128>;
+  using ClusterShape = Shape<_2, _1, _1>;
+  using Cutlass3xGemm =
+      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
+                      KernelSchedule, EpilogueSchedule>;
+};
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue>
+struct sm90_int8_config_M64 {
+  // For M in (32, 64] and any N
+  static_assert(std::is_same<InType, int8_t>());
+  using KernelSchedule = typename cutlass::gemm::KernelTmaWarpSpecialized;
+  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
+  using TileShape = Shape<_64, _64, _256>;
+  using ClusterShape = Shape<_1, _1, _1>;
+  using Cutlass3xGemm =
+      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
+                      KernelSchedule, EpilogueSchedule>;
+};
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue>
+struct sm90_int8_config_M32_NBig {
+  // For M in [1, 32] and N >= 8192
+  static_assert(std::is_same<InType, int8_t>());
+  using KernelSchedule = typename cutlass::gemm::KernelTmaWarpSpecialized;
+  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
+  using TileShape = Shape<_64, _128, _256>;
+  using ClusterShape = Shape<_1, _4, _1>;
+  using Cutlass3xGemm =
+      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
+                      KernelSchedule, EpilogueSchedule>;
+};
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue>
+struct sm90_int8_config_M32_NSmall {
+  // For M in [1, 32] and N < 8192
+  static_assert(std::is_same<InType, int8_t>());
+  using KernelSchedule = typename cutlass::gemm::KernelTmaWarpSpecialized;
+  using EpilogueSchedule = typename cutlass::epilogue::TmaWarpSpecialized;
+  using TileShape = Shape<_64, _64, _256>;
+  using ClusterShape = Shape<_1, _8, _1>;
+  using Cutlass3xGemm =
+      cutlass_3x_gemm<InType, OutType, Epilogue, TileShape, ClusterShape,
+                      KernelSchedule, EpilogueSchedule>;
+};
+
+template <typename InType, typename OutType,
+          template <typename, typename, typename> typename Epilogue,
+          typename... EpilogueArgs>
+inline void cutlass_gemm_sm90_int8_dispatch(torch::Tensor& out,
+                                            torch::Tensor const& a,
+                                            torch::Tensor const& b,
+                                            EpilogueArgs&&... args) {
+  static_assert(std::is_same<InType, int8_t>());
+  TORCH_CHECK(a.dtype() == torch::kInt8);
+  TORCH_CHECK(b.dtype() == torch::kInt8);
+
+  using Cutlass3xGemmDefault =
+      typename sm90_int8_config_default<InType, OutType,
+                                        Epilogue>::Cutlass3xGemm;
+  using Cutlass3xGemmM128 =
+      typename sm90_int8_config_M128<InType, OutType, Epilogue>::Cutlass3xGemm;
+  using Cutlass3xGemmM64 =
+      typename sm90_int8_config_M64<InType, OutType, Epilogue>::Cutlass3xGemm;
+  using Cutlass3xGemmM32NBig =
+      typename sm90_int8_config_M32_NBig<InType, OutType,
+                                         Epilogue>::Cutlass3xGemm;
+  using Cutlass3xGemmM32NSmall =
+      typename sm90_int8_config_M32_NSmall<InType, OutType,
+                                           Epilogue>::Cutlass3xGemm;
+
+  uint32_t const n = out.size(1);
+  bool const is_small_n = n < 8192;
+
+  uint32_t const m = a.size(0);
+  uint32_t const mp2 =
+      std::max(static_cast<uint32_t>(32), next_pow_2(m));  // next power of 2
+
+  if (mp2 <= 32) {
+    // m in [1, 32]
+    if (is_small_n) {
+      return cutlass_gemm_caller<Cutlass3xGemmM32NSmall>(
+          out, a, b, std::forward<EpilogueArgs>(args)...);
+    } else {
+      return cutlass_gemm_caller<Cutlass3xGemmM32NBig>(
+          out, a, b, std::forward<EpilogueArgs>(args)...);
+    }
+  } else if (mp2 <= 64) {
+    // m in (32, 64]
+    return cutlass_gemm_caller<Cutlass3xGemmM64>(
+        out, a, b, std::forward<EpilogueArgs>(args)...);
+  } else if (mp2 <= 128) {
+    // m in (64, 128]
+    return cutlass_gemm_caller<Cutlass3xGemmM128>(
+        out, a, b, std::forward<EpilogueArgs>(args)...);
+  } else {
+    // m in (128, inf)
+    return cutlass_gemm_caller<Cutlass3xGemmDefault>(
+        out, a, b, std::forward<EpilogueArgs>(args)...);
+  }
+}
+
+}  // namespace vllm