[12/n] final _C library kernel migration (#45415)

CMakeLists.txt

@@ -319,82 +319,35 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
 endif()
 
 #
-# _C extension
+# Legacy _C extension (ROCm only — CUDA ops migrated to _C_stable_libtorch)
 #
 
-set(VLLM_EXT_SRC
+if(VLLM_GPU_LANG STREQUAL "HIP")
-  "csrc/quantization/activation_kernels.cu"
+  set(VLLM_EXT_SRC
-  "csrc/torch_bindings.cpp")
+    "csrc/torch_bindings.cpp"
-
-if(VLLM_GPU_LANG STREQUAL "CUDA")
-  SET(CUTLASS_ENABLE_HEADERS_ONLY ON CACHE BOOL "Enable only the header library")
-
-  # Set CUTLASS_REVISION. Used for FetchContent. Also fixes some bogus messages when building.
-  set(CUTLASS_REVISION "v4.4.2")
-
-  # Use the specified CUTLASS source directory for compilation if VLLM_CUTLASS_SRC_DIR is provided
-  if (DEFINED ENV{VLLM_CUTLASS_SRC_DIR})
-    set(VLLM_CUTLASS_SRC_DIR $ENV{VLLM_CUTLASS_SRC_DIR})
-  endif()
-
-  if(VLLM_CUTLASS_SRC_DIR)
-    if(NOT IS_ABSOLUTE VLLM_CUTLASS_SRC_DIR)
-      get_filename_component(VLLM_CUTLASS_SRC_DIR "${VLLM_CUTLASS_SRC_DIR}" ABSOLUTE)
-    endif()
-    message(STATUS "The VLLM_CUTLASS_SRC_DIR is set, using ${VLLM_CUTLASS_SRC_DIR} for compilation")
-    FetchContent_Declare(cutlass SOURCE_DIR ${VLLM_CUTLASS_SRC_DIR})
-  else()
-    FetchContent_Declare(
-        cutlass
-        GIT_REPOSITORY https://github.com/nvidia/cutlass.git
-        # Please keep this in sync with CUTLASS_REVISION line above.
-        GIT_TAG ${CUTLASS_REVISION}
-        GIT_PROGRESS TRUE
-
-        # Speed up CUTLASS download by retrieving only the specified GIT_TAG instead of the history.
-        # Important: If GIT_SHALLOW is enabled then GIT_TAG works only with branch names and tags.
-        # So if the GIT_TAG above is updated to a commit hash, GIT_SHALLOW must be set to FALSE
-        GIT_SHALLOW TRUE
-    )
-  endif()
-  FetchContent_MakeAvailable(cutlass)
-
-  set_gencode_flags_for_srcs(
-    SRCS "${VLLM_EXT_SRC}"
-    CUDA_ARCHS "${CUDA_ARCHS}")
-
-# if CUDA endif
-endif()
-
-if (VLLM_GPU_LANG STREQUAL "HIP")
-  # Add QuickReduce kernels (ROCm-only; not part of stable ABI migration).
-  # TODO: Remove the cuda_view when ROCm upgrade to torch 2.11.
-  list(APPEND VLLM_EXT_SRC
     "csrc/custom_quickreduce.cu"
     "csrc/cuda_view.cu"
-    "csrc/libtorch_stable/cuda_utils_kernels.cu"
+    "csrc/libtorch_stable/cuda_utils_kernels.cu")
-  )
-# if ROCM endif
-endif()
 
-message(STATUS "Enabling C extension.")
+  message(STATUS "Enabling C extension.")
-define_extension_target(
+  define_extension_target(
-  _C
+    _C
-  DESTINATION vllm
+    DESTINATION vllm
-  LANGUAGE ${VLLM_GPU_LANG}
+    LANGUAGE ${VLLM_GPU_LANG}
-  SOURCES ${VLLM_EXT_SRC}
+    SOURCES ${VLLM_EXT_SRC}
-  COMPILE_FLAGS ${VLLM_GPU_FLAGS}
+    COMPILE_FLAGS ${VLLM_GPU_FLAGS}
-  ARCHITECTURES ${VLLM_GPU_ARCHES}
+    ARCHITECTURES ${VLLM_GPU_ARCHES}
-  INCLUDE_DIRECTORIES ${CUTLASS_INCLUDE_DIR}
+    INCLUDE_DIRECTORIES ${CUTLASS_INCLUDE_DIR}
-  INCLUDE_DIRECTORIES ${CUTLASS_TOOLS_UTIL_INCLUDE_DIR}
+    INCLUDE_DIRECTORIES ${CUTLASS_TOOLS_UTIL_INCLUDE_DIR}
-  USE_SABI 3
+    USE_SABI 3
-  WITH_SOABI)
+    WITH_SOABI)
 
-# If CUTLASS is compiled on NVCC >= 12.5, it by default uses
+  # If CUTLASS is compiled on NVCC >= 12.5, it by default uses
-# cudaGetDriverEntryPointByVersion as a wrapper to avoid directly calling the
+  # cudaGetDriverEntryPointByVersion as a wrapper to avoid directly calling the
-# driver API. This causes problems when linking with earlier versions of CUDA.
+  # driver API. This causes problems when linking with earlier versions of CUDA.
-# Setting this variable sidesteps the issue by calling the driver directly.
+  # Setting this variable sidesteps the issue by calling the driver directly.
-target_compile_definitions(_C PRIVATE CUTLASS_ENABLE_DIRECT_CUDA_DRIVER_CALL=1)
+  target_compile_definitions(_C PRIVATE CUTLASS_ENABLE_DIRECT_CUDA_DRIVER_CALL=1)
+endif() # _C HIP endif
 
 if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
   #
@@ -403,6 +356,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
   set(VLLM_STABLE_EXT_SRC
     "csrc/libtorch_stable/torch_bindings.cpp"
     "csrc/libtorch_stable/activation_kernels.cu"
+    "csrc/libtorch_stable/quantization/activation_kernels.cu"
     "csrc/libtorch_stable/quantization/w8a8/int8/scaled_quant.cu"
     "csrc/libtorch_stable/quantization/w8a8/fp8/common.cu"
     "csrc/libtorch_stable/quantization/w8a8/fp8/per_token_group_quant.cu"
@@ -429,6 +383,38 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
     "csrc/libtorch_stable/fused_deepseek_v4_qnorm_rope_kv_insert_kernel.cu")
 
   if(VLLM_GPU_LANG STREQUAL "CUDA")
+    SET(CUTLASS_ENABLE_HEADERS_ONLY ON CACHE BOOL "Enable only the header library")
+
+    # Set CUTLASS_REVISION. Used for FetchContent. Also fixes some bogus messages when building.
+    set(CUTLASS_REVISION "v4.4.2")
+
+    # Use the specified CUTLASS source directory for compilation if VLLM_CUTLASS_SRC_DIR is provided
+    if (DEFINED ENV{VLLM_CUTLASS_SRC_DIR})
+      set(VLLM_CUTLASS_SRC_DIR $ENV{VLLM_CUTLASS_SRC_DIR})
+    endif()
+
+    if(VLLM_CUTLASS_SRC_DIR)
+      if(NOT IS_ABSOLUTE VLLM_CUTLASS_SRC_DIR)
+        get_filename_component(VLLM_CUTLASS_SRC_DIR "${VLLM_CUTLASS_SRC_DIR}" ABSOLUTE)
+      endif()
+      message(STATUS "The VLLM_CUTLASS_SRC_DIR is set, using ${VLLM_CUTLASS_SRC_DIR} for compilation")
+      FetchContent_Declare(cutlass SOURCE_DIR ${VLLM_CUTLASS_SRC_DIR})
+    else()
+      FetchContent_Declare(
+          cutlass
+          GIT_REPOSITORY https://github.com/nvidia/cutlass.git
+          # Please keep this in sync with CUTLASS_REVISION line above.
+          GIT_TAG ${CUTLASS_REVISION}
+          GIT_PROGRESS TRUE
+
+          # Speed up CUTLASS download by retrieving only the specified GIT_TAG instead of the history.
+          # Important: If GIT_SHALLOW is enabled then GIT_TAG works only with branch names and tags.
+          # So if the GIT_TAG above is updated to a commit hash, GIT_SHALLOW must be set to FALSE
+          GIT_SHALLOW TRUE
+      )
+    endif()
+    FetchContent_MakeAvailable(cutlass)
+
     list(APPEND VLLM_STABLE_EXT_SRC
       "csrc/libtorch_stable/cuda_view.cu"
       "csrc/libtorch_stable/cuda_utils_kernels.cu"
@@ -929,7 +915,6 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
       SRCS "${FP4_SM120_SRCS}"
       CUDA_ARCHS "${FP4_SM120_ARCHS}")
     list(APPEND VLLM_STABLE_EXT_SRC "${FP4_SM120_SRCS}")
-    target_compile_definitions(_C PRIVATE ENABLE_NVFP4_SM120=1)
     list(APPEND VLLM_GPU_FLAGS "-DENABLE_NVFP4_SM120=1")
     list(APPEND VLLM_GPU_FLAGS "-DENABLE_CUTLASS_MOE_SM120=1")
     message(STATUS "Building SM12x NVFP4 for archs: ${FP4_SM120_ARCHS}")
@@ -962,7 +947,6 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
       SRCS "${FP4_SM100_SRCS}"
       CUDA_ARCHS "${FP4_SM100_ARCHS}")
     list(APPEND VLLM_STABLE_EXT_SRC "${FP4_SM100_SRCS}")
-    target_compile_definitions(_C PRIVATE ENABLE_NVFP4_SM100=1)
     list(APPEND VLLM_GPU_FLAGS "-DENABLE_NVFP4_SM100=1")
     list(APPEND VLLM_GPU_FLAGS "-DENABLE_CUTLASS_MOE_SM100=1")
     message(STATUS "Building SM10x/11x NVFP4/MXFP4 for archs: ${FP4_SM100_ARCHS}")

cmake/external_projects/qutlass.cmake

@@ -60,6 +60,7 @@ endif()
 
 if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND QUTLASS_ARCHS)
   set(QUTLASS_SOURCES
+    csrc/qutlass_registration.cpp
     ${qutlass_SOURCE_DIR}/qutlass/csrc/bindings.cpp
     ${qutlass_SOURCE_DIR}/qutlass/csrc/gemm.cu
     ${qutlass_SOURCE_DIR}/qutlass/csrc/gemm_ada.cu
@@ -78,8 +79,19 @@ if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND QUTLASS_ARCHS)
 
   if(CUTLASS_INCLUDE_DIR AND EXISTS "${CUTLASS_INCLUDE_DIR}/cutlass/cutlass.h")
     list(APPEND QUTLASS_INCLUDES "${CUTLASS_INCLUDE_DIR}")
+    if(CUTLASS_TOOLS_UTIL_INCLUDE_DIR AND
+       EXISTS "${CUTLASS_TOOLS_UTIL_INCLUDE_DIR}/cutlass/util/packed_stride.hpp")
+      list(APPEND QUTLASS_INCLUDES "${CUTLASS_TOOLS_UTIL_INCLUDE_DIR}")
+    else()
+      get_filename_component(_qutlass_cutlass_root "${CUTLASS_INCLUDE_DIR}" DIRECTORY)
+      if(EXISTS "${_qutlass_cutlass_root}/tools/util/include/cutlass/util/packed_stride.hpp")
+        list(APPEND QUTLASS_INCLUDES "${_qutlass_cutlass_root}/tools/util/include")
+      endif()
+    endif()
   elseif(EXISTS "${qutlass_SOURCE_DIR}/qutlass/third_party/cutlass/include/cutlass/cutlass.h")
-    list(APPEND QUTLASS_INCLUDES "${qutlass_SOURCE_DIR}/qutlass/third_party/cutlass/include")
+    list(APPEND QUTLASS_INCLUDES
+      "${qutlass_SOURCE_DIR}/qutlass/third_party/cutlass/include"
+      "${qutlass_SOURCE_DIR}/qutlass/third_party/cutlass/tools/util/include")
     message(STATUS "[QUTLASS] Using QuTLASS vendored CUTLASS headers (no vLLM CUTLASS detected).")
   else()
     message(FATAL_ERROR "[QUTLASS] CUTLASS headers not found. "
@@ -91,12 +103,23 @@ if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND QUTLASS_ARCHS)
     CUDA_ARCHS "${QUTLASS_ARCHS}"
   )
 
-  target_sources(_C PRIVATE ${QUTLASS_SOURCES})
+  # QuTLASS uses legacy ATen headers and cannot be built with TORCH_TARGET_VERSION.
-  target_include_directories(_C PRIVATE ${QUTLASS_INCLUDES})
+  # Keep it as its own extension (registers torch.ops._qutlass_C).
-  target_compile_definitions(_C PRIVATE
+  define_extension_target(
+    _qutlass_C
+    DESTINATION vllm
+    LANGUAGE ${VLLM_GPU_LANG}
+    SOURCES ${QUTLASS_SOURCES}
+    COMPILE_FLAGS ${VLLM_GPU_FLAGS}
+    ARCHITECTURES ${VLLM_GPU_ARCHES}
+    INCLUDE_DIRECTORIES ${QUTLASS_INCLUDES}
+    USE_SABI 3
+    WITH_SOABI)
+
+  target_compile_definitions(_qutlass_C PRIVATE
     QUTLASS_DISABLE_PYBIND=1
     TARGET_CUDA_ARCH=${QUTLASS_TARGET_CC}
-  )
+    CUTLASS_ENABLE_DIRECT_CUDA_DRIVER_CALL=1)
 
   set_property(SOURCE ${QUTLASS_SOURCES} APPEND PROPERTY COMPILE_OPTIONS
     $<$<COMPILE_LANGUAGE:CUDA>:--expt-relaxed-constexpr --use_fast_math -O3>
@@ -111,4 +134,5 @@ else()
       "[QUTLASS] Skipping build: no supported arch (12.0f / 10.0f) found in "
       "CUDA_ARCHS='${CUDA_ARCHS}'.")
   endif()
+  add_custom_target(_qutlass_C)
 endif()

csrc/libtorch_stable/moe/moe_align_sum_kernels.cu

@@ -9,7 +9,7 @@
 #include <torch/headeronly/core/ScalarType.h>
 
 #include "../../cuda_compat.h"
-#include "core/math.hpp"
+#include "libtorch_stable/core/math.hpp"
 #include "libtorch_stable/dispatch_utils.h"
 #include "libtorch_stable/torch_utils.h"
 

csrc/libtorch_stable/ops.h

@@ -2,9 +2,25 @@
 
 #include <torch/csrc/stable/library.h>
 #include <torch/csrc/stable/tensor.h>
+#include <torch/headeronly/util/Exception.h>
 
 #include <optional>
 #include <string>
+#include <vector>
+
+#include <torch/csrc/stable/ops.h>
+
+inline torch::stable::Tensor weak_ref_tensor(torch::stable::Tensor& tensor) {
+  // Ensure tensor is on CUDA
+  STD_TORCH_CHECK(tensor.device().is_cuda(), "Tensor must be on CUDA device");
+
+  // Get the raw data pointer
+  void* data_ptr = tensor.mutable_data_ptr();
+
+  /// Create a new tensor from the raw data pointer
+  return torch::stable::from_blob(data_ptr, tensor.sizes(), tensor.strides(),
+                                  tensor.device(), tensor.scalar_type());
+}
 
 void per_token_group_quant_fp8(const torch::stable::Tensor& input,
                                torch::stable::Tensor& output_q,
@@ -371,6 +387,18 @@ void silu_and_mul(torch::stable::Tensor& out, torch::stable::Tensor& input);
 void silu_and_mul_clamp(torch::stable::Tensor& out,
                         torch::stable::Tensor& input, double limit,
                         double alpha = 1.0, double beta = 0.0);
+
+void silu_and_mul_quant(torch::stable::Tensor& out,
+                        torch::stable::Tensor& input,
+                        torch::stable::Tensor& scale);
+
+void persistent_masked_m_silu_mul_quant(
+    const torch::stable::Tensor& input,              // (E, T, 2*H)
+    const torch::stable::Tensor& tokens_per_expert,  // (E)
+    torch::stable::Tensor& y_q,                      // (E, T, H) [OUT]
+    torch::stable::Tensor& y_s,  // (E, T, H//group_size) [OUT]
+    bool use_ue8m0);
+
 void mul_and_silu(torch::stable::Tensor& out, torch::stable::Tensor& input);
 void gelu_and_mul(torch::stable::Tensor& out, torch::stable::Tensor& input);
 void gelu_tanh_and_mul(torch::stable::Tensor& out,

csrc/libtorch_stable/quantization/activation_kernels.cu

@@ -1,16 +1,12 @@
-#include <ATen/cuda/CUDAContext.h>
+#include "libtorch_stable/torch_utils.h"
-#include <torch/all.h>
-#include <c10/cuda/CUDAGuard.h>
 
 #include <cmath>
-#include "core/math.hpp"
-#include "../cuda_compat.h"
-#include "dispatch_utils.h"
 
+#include "libtorch_stable/core/math.hpp"
+#include "cuda_compat.h"
+#include "libtorch_stable/dispatch_utils.h"
 #include "quantization/w8a8/fp8/common.cuh"
 
-#include <c10/util/Float8_e4m3fn.h>
-
 #ifndef USE_ROCM
   #include <cuda_bf16.h>
   #include <cuda_fp16.h>
@@ -33,7 +29,6 @@ typedef __hip_fp8x4_e4m3_fnuz __nv_fp8x4_e4m3;
   #endif
 #endif
 
-#include "core/registration.h"
 namespace vllm {
 
 template <typename T>
@@ -564,41 +559,47 @@ __global__ void silu_mul_fp8_quant_deep_gemm_kernel(
 }  // namespace vllm
 
 // Launch activation, gating, and quantize kernel.
-#define LAUNCH_ACTIVATION_GATE_KERNEL(KERNEL)                               \
+#define LAUNCH_ACTIVATION_GATE_KERNEL(KERNEL)                             \
-  int d = input.size(-1) / 2;                                               \
+  int d = input.size(-1) / 2;                                             \
-  int64_t num_tokens = input.numel() / input.size(-1);                      \
+  int64_t num_tokens = input.numel() / input.size(-1);                    \
-  dim3 grid(num_tokens, num_tokens > 16 ? num_tokens > 32 ? 1 : 2 : 4);     \
+  dim3 grid(num_tokens, num_tokens > 16 ? num_tokens > 32 ? 1 : 2 : 4);   \
-  dim3 block(std::min(d, 512));                                             \
+  dim3 block(std::min(d, 512));                                           \
-  const at::cuda::OptionalCUDAGuard device_guard(device_of(input));         \
+  const torch::stable::accelerator::DeviceGuard device_guard(             \
-  const cudaStream_t stream = at::cuda::getCurrentCUDAStream();             \
+      input.get_device_index());                                          \
-  VLLM_DISPATCH_FLOATING_TYPES(                                             \
+  const cudaStream_t stream =                                             \
-      input.scalar_type(), "act_and_mul_kernel", [&] {                      \
+      get_current_cuda_stream(input.get_device_index());                  \
-        VLLM_DISPATCH_FP8_TYPES(                                            \
+  VLLM_STABLE_DISPATCH_FLOATING_TYPES(                                    \
-            out.scalar_type(), "fused_add_rms_norm_kernel_fp8_type", [&] {  \
+      input.scalar_type(), "act_and_mul_kernel", [&] {                    \
-              vllm::act_and_mul_quant_kernel<scalar_t, KERNEL<scalar_t>,    \
+        VLLM_STABLE_DISPATCH_FP8_TYPES(                                   \
-                                             fp8_t>                         \
+            out.scalar_type(), "act_and_mul_quant_kernel_fp8_type", [&] { \
-                  <<<grid, block, 0, stream>>>(out.data_ptr<fp8_t>(),       \
+              vllm::act_and_mul_quant_kernel<scalar_t, KERNEL<scalar_t>,  \
-                                               input.data_ptr<scalar_t>(),  \
+                                             fp8_t>                       \
-                                               scale.data_ptr<float>(), d); \
+                  <<<grid, block, 0, stream>>>(                           \
-            });                                                             \
+                      out.mutable_data_ptr<fp8_t>(),                      \
+                      input.const_data_ptr<scalar_t>(),                   \
+                      scale.const_data_ptr<float>(), d);                  \
+            });                                                           \
       });
 
-void silu_and_mul_quant(torch::Tensor& out,    // [..., d]
+void silu_and_mul_quant(torch::stable::Tensor& out,    // [..., d]
-                        torch::Tensor& input,  // [..., 2 * d]
+                        torch::stable::Tensor& input,  // [..., 2 * d]
-                        torch::Tensor& scale) {
+                        torch::stable::Tensor& scale) {
-  TORCH_CHECK(out.dtype() == torch::kFloat8_e4m3fn ||
+  STD_TORCH_CHECK(
-              out.dtype() == torch::kFloat8_e4m3fnuz);
+      out.scalar_type() == torch::headeronly::ScalarType::Float8_e4m3fn ||
-  TORCH_CHECK(input.dtype() == torch::kFloat16 ||
+      out.scalar_type() == torch::headeronly::ScalarType::Float8_e4m3fnuz);
-              input.dtype() == torch::kBFloat16);
+  STD_TORCH_CHECK(
-  TORCH_CHECK(input.size(-1) % 2 == 0);
+      input.scalar_type() == torch::headeronly::ScalarType::Half ||
+          input.scalar_type() == torch::headeronly::ScalarType::BFloat16,
+      "Input must be FP16 or BF16");
+  STD_TORCH_CHECK(input.size(-1) % 2 == 0);
   LAUNCH_ACTIVATION_GATE_KERNEL(vllm::silu_kernel);
 }
 
 void persistent_masked_m_silu_mul_quant(
-    const at::Tensor& input,              // (E, T, 2*H)
+    const torch::stable::Tensor& input,              // (E, T, 2*H)
-    const at::Tensor& tokens_per_expert,  // (E)
+    const torch::stable::Tensor& tokens_per_expert,  // (E)
-    at::Tensor& y_q,                      // (E, T, H) [OUT]
+    torch::stable::Tensor& y_q,                      // (E, T, H) [OUT]
-    at::Tensor& y_s,                      // (E, T, H//group_size) [OUT]
+    torch::stable::Tensor& y_s,  // (E, T, H//group_size) [OUT]
     bool cast_scale_ue8m0) {
 #ifndef USE_ROCM
 
@@ -606,14 +607,18 @@ void persistent_masked_m_silu_mul_quant(
   // fixed GROUP_SIZE of 128.
   static constexpr int GROUP_SIZE = 128;
 
-  TORCH_CHECK(input.dtype() == torch::kBFloat16);
+  STD_TORCH_CHECK(input.scalar_type() ==
-  TORCH_CHECK(y_q.dtype() == torch::kFloat8_e4m3fn ||
+                  torch::headeronly::ScalarType::BFloat16);
-              y_q.dtype() == torch::kFloat8_e4m3fnuz);
+  STD_TORCH_CHECK(
-  TORCH_CHECK(input.size(-1) % (GROUP_SIZE * 2) == 0);
+      y_q.scalar_type() == torch::headeronly::ScalarType::Float8_e4m3fn ||
+      y_q.scalar_type() == torch::headeronly::ScalarType::Float8_e4m3fnuz);
+  STD_TORCH_CHECK(input.size(-1) % (GROUP_SIZE * 2) == 0);
 
   bool const is_packed_ue8m0 =
-      (y_s.dtype() == torch::kInt32 && cast_scale_ue8m0);
+      (y_s.scalar_type() == torch::headeronly::ScalarType::Int &&
-  TORCH_CHECK(y_s.dtype() == torch::kFloat32 || is_packed_ue8m0);
+       cast_scale_ue8m0);
+  STD_TORCH_CHECK(y_s.scalar_type() == torch::headeronly::ScalarType::Float ||
+                  is_packed_ue8m0);
 
   using Idx_t = int64_t;
 
@@ -631,7 +636,7 @@ void persistent_masked_m_silu_mul_quant(
 
   int const NUM_GROUPS = H / GROUP_SIZE;
 
-  const cudaStream_t stream = at::cuda::getCurrentCUDAStream();
+  const cudaStream_t stream = get_current_cuda_stream(input.get_device_index());
 
   // TODO: Get this from cuda_arch ?
   static constexpr int SILU_V2_BLOCK_COUNT = 132 * 32;
@@ -643,18 +648,21 @@ void persistent_masked_m_silu_mul_quant(
     static constexpr int max_shared_mem_bytes =                                \
         GROUP_SIZE * 2 * STAGES * NUM_WARPS * 2;                               \
     dim3 grid(sms), block(THREAD_COUNT);                                       \
-    const at::cuda::OptionalCUDAGuard device_guard(device_of(input));          \
+    const torch::stable::accelerator::DeviceGuard device_guard(                \
-    VLLM_DISPATCH_FP8_TYPES(                                                   \
+        input.get_device_index());                                             \
+    VLLM_STABLE_DISPATCH_FP8_TYPES(                                            \
         y_q.scalar_type(), "silu_mul_fp8_quant_deep_gemm_kernel", [&] {        \
           vllm::silu_mul_fp8_quant_deep_gemm_kernel<                           \
               BLOCK_COUNT, max_shared_mem_bytes, fp8_t, scale_t, THREAD_COUNT, \
               Idx_t, CEIL_UE8M0, GROUP_SIZE, STAGES>                           \
               <<<grid, block, max_shared_mem_bytes + (E + 1) * 16, stream>>>(  \
-                  reinterpret_cast<__nv_bfloat16*>(input.data_ptr()),          \
+                  reinterpret_cast<const __nv_bfloat16*>(                      \
-                  (fp8_t*)y_q.data_ptr(),                                      \
+                      input.const_data_ptr()),                                 \
-                  reinterpret_cast<scale_t*>(y_s.data_ptr()),                  \
+                  y_q.mutable_data_ptr<fp8_t>(),                               \
-                  reinterpret_cast<int32_t*>(tokens_per_expert.data_ptr()), E, \
+                  reinterpret_cast<scale_t*>(y_s.mutable_data_ptr()),          \
-                  T, H, stride_i_e, stride_i_t, stride_i_h, stride_yq_e,       \
+                  reinterpret_cast<const int32_t*>(                            \
+                      tokens_per_expert.const_data_ptr()),                     \
+                  E, T, H, stride_i_e, stride_i_t, stride_i_h, stride_yq_e,    \
                   stride_yq_t, stride_yq_h, STRIDE_YS_E, STRIDE_YS_T,          \
                   STRIDE_YS_G, STRIDE_YS_P, stride_counts_e);                  \
         });
@@ -679,7 +687,7 @@ void persistent_masked_m_silu_mul_quant(
   Idx_t stride_ys_g = y_s.stride(2);
   Idx_t stride_ys_p = 0;
   if (!cast_scale_ue8m0) {
-    TORCH_CHECK(!is_packed_ue8m0);
+    STD_TORCH_CHECK(!is_packed_ue8m0);
     LAUNCH_ON_H(float, stride_ys_e, stride_ys_t, stride_ys_g, stride_ys_p,
                 false);
     return;
@@ -692,8 +700,8 @@ void persistent_masked_m_silu_mul_quant(
     return;
   }
 
-  TORCH_CHECK(cast_scale_ue8m0 && is_packed_ue8m0);
+  STD_TORCH_CHECK(cast_scale_ue8m0 && is_packed_ue8m0);
-  TORCH_CHECK(y_s.dtype() == torch::kInt32);
+  STD_TORCH_CHECK(y_s.scalar_type() == torch::headeronly::ScalarType::Int);
 
   // Int32 packed ue8m0 scales tensor.
   // Let E, T, G be the number to experts, number of tokens and number of groups

csrc/libtorch_stable/quantization/fp4/nvfp4_scaled_mm_kernels.cu

@@ -31,7 +31,7 @@
 
 #include "cutlass/util/packed_stride.hpp"
 
-#include "core/math.hpp"
+#include "libtorch_stable/core/math.hpp"
 #include "core/batch_invariant.hpp"
 
 using namespace cute;

csrc/libtorch_stable/quantization/fp4/nvfp4_scaled_mm_sm120_kernels.cu

@@ -31,7 +31,7 @@
 
 #include "cutlass/util/packed_stride.hpp"
 
-#include "core/math.hpp"
+#include "libtorch_stable/core/math.hpp"
 #include "core/batch_invariant.hpp"
 
 using namespace cute;

csrc/libtorch_stable/quantization/w8a8/cutlass/c3x/cutlass_gemm_caller.cuh

@@ -19,7 +19,7 @@
 #include "cutlass/gemm/collective/collective_builder.hpp"
 #include "cutlass/util/packed_stride.hpp"
 
-#include "core/math.hpp"
+#include "libtorch_stable/core/math.hpp"
 #include "libtorch_stable/cutlass_extensions/common.hpp"
 // clang-format on
 

csrc/libtorch_stable/quantization/w8a8/cutlass/c3x/scaled_mm.cuh

@@ -14,7 +14,7 @@
 #include "cutlass/epilogue/collective/collective_builder.hpp"
 #include "cutlass/gemm/collective/collective_builder.hpp"
 
-#include "core/math.hpp"
+#include "libtorch_stable/core/math.hpp"
 #include "libtorch_stable/cutlass_extensions/common.hpp"
 // clang-format on
 

csrc/libtorch_stable/quantization/w8a8/cutlass/scaled_mm_c2x.cuh

@@ -22,7 +22,7 @@
 #include "cutlass/epilogue/threadblock/fusion/visitors.hpp"
 #include "cutlass/gemm/kernel/default_gemm_universal_with_visitor.h"
 
-#include "core/math.hpp"
+#include "libtorch_stable/core/math.hpp"
 #include "libtorch_stable/cutlass_extensions/common.hpp"
 // clang-format on
 

csrc/libtorch_stable/torch_bindings.cpp

@@ -34,6 +34,20 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
   // TODO: Remove this once ROCm upgrade to torch 2.11.
   ops.def("get_cuda_view_from_cpu_tensor(Tensor cpu_tensor) -> Tensor");
 
+  // Note about marlin kernel 'workspace' arguments:
+  // Technically these should be mutable since they are modified by the kernel.
+  // But since they are set back to zero once the kernel is finished we can
+  // hand wave and say that they have no net effect.
+  //
+  // The reason to mark 'workspace' as immutable is so that they don't interfere
+  // with using ScalarType arguments in the ops. If they are marked as mutable,
+  // pytorch throws an assert in
+  // 'torch._higher_order_ops._register_effectful_op' that prevents these
+  // kernels from being torch.compile'd.
+  // See the following document for more info on custom types and ops that use
+  // custom types:
+  // https://docs.google.com/document/d/18fBMPuOJ0fY5ZQ6YyrHUppw9FA332CpNtgB6SOIgyuA
+
   // Machete (Dense) Optimized Mixed Precision GEMM for Hopper.
   ops.def(
       "machete_supported_schedules("
@@ -480,6 +494,11 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
       "Tensor workspace, int k, int max_seq_len) -> ()");
 
   // Activation ops
+  ops.def(
+      "persistent_masked_m_silu_mul_quant(Tensor input, Tensor counts, Tensor! "
+      "y_q, Tensor! y_s, bool use_ue8m0) -> ()");
+  ops.def("weak_ref_tensor(Tensor input) -> Tensor");
+
   // Activation function used in SwiGLU.
   ops.def("silu_and_mul(Tensor! result, Tensor input) -> ()");
 
@@ -492,6 +511,10 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
       "silu_and_mul_with_clamp(Tensor! result, Tensor input, float limit, "
       "float alpha=1.0, float beta=0.0) -> ()");
 
+  // SwiGLU activation with FP8 quantization.
+  ops.def(
+      "silu_and_mul_quant(Tensor! result, Tensor input, Tensor scale) -> ()");
+
   // Activation function used in GeGLU with `none` approximation.
   ops.def("gelu_and_mul(Tensor! out, Tensor input) -> ()");
 
@@ -690,6 +713,10 @@ STABLE_TORCH_LIBRARY_IMPL(_C, CUDA, ops) {
   ops.impl("persistent_topk", TORCH_BOX(&persistent_topk));
 
   // Activation kernels (shared CUDA/ROCm)
+  ops.impl("persistent_masked_m_silu_mul_quant",
+           TORCH_BOX(&persistent_masked_m_silu_mul_quant));
+  ops.impl("weak_ref_tensor", TORCH_BOX(&weak_ref_tensor));
+  ops.impl("silu_and_mul_quant", TORCH_BOX(&silu_and_mul_quant));
   ops.impl("silu_and_mul", TORCH_BOX(&silu_and_mul));
   ops.impl("mul_and_silu", TORCH_BOX(&mul_and_silu));
   ops.impl("gelu_and_mul", TORCH_BOX(&gelu_and_mul));

csrc/ops.h

@@ -9,28 +9,6 @@
 
 #include <vector>
 
-torch::Tensor weak_ref_tensor(torch::Tensor& tensor) {
-  // Ensure tensor is on CUDA
-  if (!tensor.is_cuda()) {
-    throw std::runtime_error("Tensor must be on CUDA device");
-  }
-
-  // Get the raw data pointer
-  void* data_ptr = tensor.data_ptr();
-
-  // Get tensor sizes and strides
-  std::vector<int64_t> sizes = tensor.sizes().vec();
-  std::vector<int64_t> strides = tensor.strides().vec();
-
-  // Get tensor options (dtype, device)
-  auto options = tensor.options();
-
-  // Create a new tensor from the raw data pointer
-  auto new_tensor = torch::from_blob(data_ptr, sizes, strides, options);
-
-  return new_tensor;
-}
-
 // rms_norm and fused_add_rms_norm declarations also exist in
 // csrc/libtorch_stable/ops.h (torch::stable ABI for CUDA). They remain here
 // because the CPU build still uses these torch::Tensor declarations.
@@ -53,16 +31,6 @@ void silu_and_mul(torch::Tensor& out, torch::Tensor& input);
 void silu_and_mul_clamp(torch::Tensor& out, torch::Tensor& input, double limit,
                         double alpha = 1.0, double beta = 0.0);
 
-void silu_and_mul_quant(torch::Tensor& out, torch::Tensor& input,
-                        torch::Tensor& scale);
-
-void persistent_masked_m_silu_mul_quant(
-    const at::Tensor& input,   // (E, T, 2*H)
-    const at::Tensor& counts,  // (E)
-    at::Tensor& y_q,           // (E, T, H) [OUT]
-    at::Tensor& y_s,           // (E, T, H//group_size) [OUT]
-    bool use_ue8m0);
-
 void gelu_and_mul(torch::Tensor& out, torch::Tensor& input);
 
 void gelu_tanh_and_mul(torch::Tensor& out, torch::Tensor& input);

csrc/qutlass_registration.cpp

@@ -0,0 +1,5 @@
+#include "core/registration.h"
+
+// QuTLASS registers torch.ops._qutlass_C via TORCH_LIBRARY in bindings.cpp.
+// This stub lets Python import vllm._qutlass_C to trigger op registration.
+REGISTER_EXTENSION(_qutlass_C)

csrc/torch_bindings.cpp

@@ -20,17 +20,6 @@
 
 TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
   // vLLM custom ops
-  //
-
-  ops.def(
-      "persistent_masked_m_silu_mul_quant(Tensor input, Tensor counts, Tensor! "
-      "y_q, Tensor! y_s,"
-      "bool use_ue8m0) -> ()");
-  ops.impl("persistent_masked_m_silu_mul_quant", torch::kCUDA,
-           &persistent_masked_m_silu_mul_quant);
-
-  ops.def("weak_ref_tensor(Tensor input) -> Tensor");
-  ops.impl("weak_ref_tensor", torch::kCUDA, &weak_ref_tensor);
 
 #ifdef USE_ROCM
   // TODO: Remove this once we upgrade to torch 2.11.
@@ -39,35 +28,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
   ops.def("get_cuda_view_from_cpu_tensor(Tensor cpu_tensor) -> Tensor");
   ops.impl("get_cuda_view_from_cpu_tensor", torch::kCPU,
            &get_cuda_view_from_cpu_tensor);
-#endif
-
-  // Activation ops (quantized only — basic ops moved to _C_stable_libtorch)
-  ops.def(
-      "silu_and_mul_quant(Tensor! result, Tensor input, Tensor scale) -> ()");
-  ops.impl("silu_and_mul_quant", torch::kCUDA, &silu_and_mul_quant);
-
-  // Horizontally-fused DeepseekV4-MLA: per-head RMSNorm + GPT-J RoPE for Q, and
-  // GPT-J RoPE + UE8M0 FP8 quant + paged cache insert for KV, all in one
-  // kernel launch. Registered in _C_stable_libtorch (incl. the FlashInfer V4
-  // full-cache bf16/fp8 variants).
-
-  // Quantization ops
-#ifndef USE_ROCM
-
-  // Note about marlin kernel 'workspace' arguments:
-  // Technically these should be mutable since they are modified by the kernel.
-  // But since they are set back to zero once the kernel is finished we can
-  // hand wave and say that they have no net effect.
-  //
-  // The reason to mark 'workspace' as immutable is so that they don't interfere
-  // with using ScalarType arguments in the ops. If they are marked as mutable,
-  // pytorch throws an assert in
-  // 'torch._higher_order_ops._register_effectful_op' that prevents these
-  // kernels from being torch.compile'd.
-  // See the following document for more info on custom types and ops that use
-  // custom types:
-  // https://docs.google.com/document/d/18fBMPuOJ0fY5ZQ6YyrHUppw9FA332CpNtgB6SOIgyuA
-
 #endif
 }
 

setup.py

@@ -769,6 +769,7 @@ class precompiled_wheel_utils:
                             "vllm/_C.abi3.so",
                             "vllm/_C_stable_libtorch.abi3.so",
                             "vllm/_moe_C_stable_libtorch.abi3.so",
+                            "vllm/_qutlass_C.abi3.so",
                             "vllm/_flashmla_C.abi3.so",
                             "vllm/_flashmla_extension_C.abi3.so",
                             "vllm/_sparse_flashmla_C.abi3.so",
@@ -1135,6 +1136,7 @@ if _is_cuda():
         # DeepGEMM requires CUDA 12.3+ (SM90/SM100)
         # Optional since it won't build on unsupported architectures
         ext_modules.append(CMakeExtension(name="vllm._deep_gemm_C", optional=True))
+        ext_modules.append(CMakeExtension(name="vllm._qutlass_C", optional=True))
     # fmha_sm100 is a Python/CuTe-DSL package installed into vllm.third_party.
     ext_modules.append(CMakeExtension(name="vllm.fmha_sm100", optional=True))
 
@@ -1149,7 +1151,8 @@ if _is_cpu():
         ext_modules.append(CMakeExtension(name="vllm._C"))
 
 if _build_custom_ops():
-    ext_modules.append(CMakeExtension(name="vllm._C"))
+    if _is_hip():
+        ext_modules.append(CMakeExtension(name="vllm._C"))
     if _is_cuda() or _is_hip():
         ext_modules.append(CMakeExtension(name="vllm._C_stable_libtorch"))
         ext_modules.append(CMakeExtension(name="vllm._moe_C_stable_libtorch"))

vllm/platforms/cuda.py

@@ -19,7 +19,6 @@ from torch.distributed.distributed_c10d import is_nccl_available
 from typing_extensions import ParamSpec
 
 # import custom ops, trigger op registration
-import vllm._C  # noqa
 import vllm._C_stable_libtorch  # noqa
 import vllm.envs as envs
 from vllm.logger import init_logger
@@ -40,6 +39,11 @@ else:
 
 logger = init_logger(__name__)
 
+try:
+    import vllm._qutlass_C  # noqa: F401
+except ImportError as e:
+    logger.warning("Failed to import from vllm._qutlass_C: %r", e)
+
 _P = ParamSpec("_P")
 _R = TypeVar("_R")
 
@@ -187,6 +191,22 @@ class CudaPlatformBase(Platform):
         "RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES",
     ]
 
+    @classmethod
+    def import_kernels(cls) -> None:
+        """Import CUDA kernel extensions (_C_stable_libtorch, optional _qutlass_C)."""
+        try:
+            import vllm._C_stable_libtorch  # noqa: F401
+        except ImportError as e:
+            logger.warning("Failed to import from vllm._C_stable_libtorch: %r", e)
+        try:
+            import vllm._moe_C_stable_libtorch  # noqa: F401
+        except ImportError as e:
+            logger.warning("Failed to import from vllm._moe_C_stable_libtorch: %r", e)
+        try:
+            import vllm._qutlass_C  # noqa: F401
+        except ImportError as e:
+            logger.warning("Failed to import from vllm._qutlass_C: %r", e)
+
     @property
     def supported_dtypes(self) -> list[torch.dtype]:
         if self.has_device_capability(80):