mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-02 04:31:25 +00:00
c3a4800c5f
* add prenorm/postnorm support, refactor using generate.py * update README * update README * fix format * update some description and fix format * update format * format * use non-raw for loading * format and update n4096 * dynamic-quant ready * update readme * support fused dynamic-quant * update fused-quant, with smooth * update README * update args * update some based on comment
12 lines
546 B
C++
12 lines
546 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/ops/topk_softmax/kernel/topk_softmax_kernel.hpp"
|
|
#include "ck_tile/ops/topk_softmax/pipeline/topk_softmax_warp_per_row_pipeline.hpp"
|
|
#include "ck_tile/ops/topk_softmax/pipeline/topk_softmax_warp_per_row_policy.hpp"
|
|
#include "ck_tile/ops/topk_softmax/pipeline/topk_softmax_warp_per_row_problem.hpp"
|
|
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
|
|
#include "ck_tile/ops/common/tensor_layout.hpp"
|