mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
ce51308aaf
* add sparse attention VSA
* fix the pre-commit
* Add jenga test and pre-commit
* add bf16 for vsa
* add jenga support bf16
* remove lse arg
* split kernel code to block & kernel
* fix the pre-commit
* fix the pre-commit
* fix the copyrights
* fix the copyright
* fix the copyright & rename block to pipeline
* fix the copyright and pipeline
* remove lse & dropout & add fmt
* fix the jenga&VSA code review
* remove the useless code & resolved the comments
* remove useless code
* remove useless code
* Clean up code
* Remove more unused code
* Re-format .hpp
* Refactor codegen scripts
---------
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
Co-authored-by: asleepzzz <hanwen.chang@amd.com>
[ROCm/composable_kernel commit: 4d2f8c111e]
54 lines
2.7 KiB
C++
54 lines
2.7 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
#pragma once
|
|
|
|
#include "ck_tile/host/arg_parser.hpp"
|
|
#include "ck_tile/host/check_err.hpp"
|
|
#include "ck_tile/host/concat.hpp"
|
|
#include "ck_tile/host/convolution_host_tensor_descriptor_helper.hpp"
|
|
#include "ck_tile/host/convolution_parameter.hpp"
|
|
#include "ck_tile/host/device_memory.hpp"
|
|
#include "ck_tile/host/device_prop.hpp"
|
|
#include "ck_tile/host/fill.hpp"
|
|
#include "ck_tile/host/flush_icache.hpp"
|
|
#include "ck_tile/host/high_res_cpu_clock.hpp"
|
|
#include "ck_tile/host/hip_check_error.hpp"
|
|
#include "ck_tile/host/host_tensor.hpp"
|
|
#include "ck_tile/host/joinable_thread.hpp"
|
|
#include "ck_tile/host/kernel_launch.hpp"
|
|
#include "ck_tile/host/permute_pk_int4.hpp"
|
|
#include "ck_tile/host/ranges.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_contraction.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_dropout.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_dropout_randval.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_elementwise.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_gemm.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_masking.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_rotary_position_embedding.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_softmax.hpp"
|
|
#include "ck_tile/host/reference/reference_batched_transpose.hpp"
|
|
#include "ck_tile/host/reference/reference_blocked_attention.hpp"
|
|
#include "ck_tile/host/reference/reference_elementwise.hpp"
|
|
#include "ck_tile/host/reference/reference_fused_moe.hpp"
|
|
#include "ck_tile/host/reference/reference_gemm.hpp"
|
|
#include "ck_tile/host/reference/reference_grouped_conv_bwd_data.hpp"
|
|
#include "ck_tile/host/reference/reference_grouped_conv_bwd_weight.hpp"
|
|
#include "ck_tile/host/reference/reference_grouped_conv_fwd.hpp"
|
|
#include "ck_tile/host/reference/reference_im2col.hpp"
|
|
#include "ck_tile/host/reference/reference_layernorm2d_fwd.hpp"
|
|
#include "ck_tile/host/reference/reference_moe_gemm.hpp"
|
|
#include "ck_tile/host/reference/reference_moe_sorting.hpp"
|
|
#include "ck_tile/host/reference/reference_permute.hpp"
|
|
#include "ck_tile/host/reference/reference_pool.hpp"
|
|
#include "ck_tile/host/reference/reference_reduce.hpp"
|
|
#include "ck_tile/host/reference/reference_rmsnorm2d_fwd.hpp"
|
|
#include "ck_tile/host/reference/reference_rowwise_quantization2d.hpp"
|
|
#include "ck_tile/host/reference/reference_softmax.hpp"
|
|
#include "ck_tile/host/reference/reference_topk.hpp"
|
|
#include "ck_tile/host/reference/reference_transpose.hpp"
|
|
#include "ck_tile/host/rotating_buffers.hpp"
|
|
#include "ck_tile/host/stream_config.hpp"
|
|
#include "ck_tile/host/stream_utils.hpp"
|
|
#include "ck_tile/host/tensor_shuffle_utils.hpp"
|
|
#include "ck_tile/host/timer.hpp"
|