mirror of
https://github.com/NVIDIA/cutlass.git
synced 2026-06-29 19:07:07 +00:00
39b352fa93
* v4.6 dev update. * Remove CUTLASS_HOST_DEVICE from CudaHostAdapater::memsetDevice (#3286) * [SM120] Add ptr-array TMA collective for tensor/token-scaled FP8 grouped GEMM (#3280) * gemm: add SM120 array TMA collective for tensor/token-scaled FP8 grouped GEMM Adds CollectiveMma and CollectiveBuilder specializations for MainloopSm120ArrayTmaWarpSpecialized, enabling ptr-array grouped GEMM (MoE expert dispatch) with tensor- and token-level FP8 scaling on SM_120/SM_121 consumer Blackwell (RTX 5090/5080/5070, DGX Spark GB10). New files: - include/cutlass/gemm/collective/sm120_mma_array_tma.hpp CollectiveMma specialization for MainloopSm120ArrayTmaWarpSpecialized. Handles both Cooperative (4x2 atom layout) and Pingpong (2x2) schedules. Grouped GEMM via pointer-array indirection through params.ptr_A / ptr_B. Supports F8F6F4 MMA with TMA loads for both A and B operands. - include/cutlass/gemm/collective/builders/sm120_array_mma_builder.inl CollectiveBuilder specialization for KernelPtrArrayTmaWarpSpecialized Cooperative/PingpongSm120<N> schedule tags. Computes tile/stage counts from smem capacity, routes to MainloopSm120ArrayTmaWarpSpecialized dispatch policy, produces correctly-typed CollectiveOp. Modified files: - collective_mma.hpp: include sm120_mma_array_tma.hpp - collective_builder.hpp: include sm120_array_mma_builder.inl - sm120_mma_builder.inl: remove ptr-array schedules from enable_if (they now route to sm120_array_mma_builder.inl) and drop the IsPtrArrayKernel static_assert that enforced the restriction Validated on real SM_121 hardware (DGX Spark, 128 GB LPDDR5X) running vLLM with RedHatAI/gemma-4-26B-A4B-it-FP8-Dynamic (Gemma 4 MoE, 26B total / 4B active). Previously fell back to a non-CUTLASS Triton path; with this patch, the SM120 CUTLASS grouped GEMM collective activates and produces correct outputs. Short-sequence throughput improved ~7% vs the fallback baseline (76.3 → 81.9 tok/s). Closes #3263 Co-authored-by: Claude <noreply@anthropic.com> Signed-off-by: Tyler Merritt <tgmerritt@gmail.com> * test: add SM120 ptr-array grouped GEMM unit tests Adds 6 device-level tests for the CollectiveMma/CollectiveBuilder specializations introduced for MainloopSm120ArrayTmaWarpSpecialized, covering both KernelPtrArrayTmaWarpSpecializedPingpongSm120<2> and KernelPtrArrayTmaWarpSpecializedCooperativeSm120<2> schedule tags across e4m3×e4m3 (symmetric), e4m3×e5m2 (mixed), float and bfloat16 outputs, and two tile shapes. Tests land in test/unit/gemm/device/sm120_tensorop_gemm/ under the new cutlass_test_unit_sm120_grouped_gemm_device_tensorop CMake target, per reviewer request in PR #3280. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Signed-off-by: Tyler Merritt <tgmerritt@gmail.com> Co-authored-by: Claude <noreply@anthropic.com> --------- Signed-off-by: Tyler Merritt <tgmerritt@gmail.com> Co-authored-by: Alex Georgiev <89279829+alexngUNC@users.noreply.github.com> Co-authored-by: Tyler <tgmerritt@gmail.com> Co-authored-by: Claude <noreply@anthropic.com>
47 lines
2.0 KiB
Python
47 lines
2.0 KiB
Python
#################################################################################################
|
|
#
|
|
# Copyright (c) 2023 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: BSD-3-Clause
|
|
#
|
|
# Redistribution and use in source and binary forms, with or without
|
|
# modification, are permitted provided that the following conditions are met:
|
|
#
|
|
# 1. Redistributions of source code must retain the above copyright notice, this
|
|
# list of conditions and the following disclaimer.
|
|
#
|
|
# 2. Redistributions in binary form must reproduce the above copyright notice,
|
|
# this list of conditions and the following disclaimer in the documentation
|
|
# and/or other materials provided with the distribution.
|
|
#
|
|
# 3. Neither the name of the copyright holder nor the names of its
|
|
# contributors may be used to endorse or promote products derived from
|
|
# this software without specific prior written permission.
|
|
#
|
|
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
|
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
|
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
|
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
|
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
#
|
|
#################################################################################################
|
|
|
|
from setuptools import setup
|
|
|
|
|
|
def perform_setup():
|
|
setup(
|
|
name='pycute',
|
|
version='4.6.0',
|
|
description='Python implementation of CuTe',
|
|
packages=['pycute'],
|
|
)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
perform_setup()
|