mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-02 04:31:25 +00:00
fbd654545a
* fix compile error * fix typo of padding * Add smoothquant op * Add smoothquant instance library * refine type * add test script * Re-generate smoothquant.hpp * Always use 'current year' in copyright * use Generic2dBlockShape instead * Add vector = 8 instance back * Find exe path automatically * Simplify the api condition * Remove debugging code * update year * Add blank line between function declaration * explicitly cast return value to dim3 * refine return value * Fix default warmup and repeat value * Add comment * refactor sommthquant cmake * Add README * Fix typo --------- Co-authored-by: Po Yen, Chen <PoYen.Chen@amd.com>
13 lines
734 B
C++
13 lines
734 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/ops/add_rmsnorm2d_rdquant/kernel/add_rmsnorm2d_rdquant_fwd_kernel.hpp"
|
|
#include "ck_tile/ops/add_rmsnorm2d_rdquant/pipeline/add_rmsnorm2d_rdquant_fwd_pipeline_default_policy.hpp"
|
|
#include "ck_tile/ops/add_rmsnorm2d_rdquant/pipeline/add_rmsnorm2d_rdquant_fwd_pipeline_one_pass.hpp"
|
|
#include "ck_tile/ops/add_rmsnorm2d_rdquant/pipeline/add_rmsnorm2d_rdquant_fwd_pipeline_problem.hpp"
|
|
#include "ck_tile/ops/add_rmsnorm2d_rdquant/pipeline/add_rmsnorm2d_rdquant_fwd_pipeline_three_pass.hpp"
|
|
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
|
|
#include "ck_tile/ops/common/tensor_layout.hpp"
|