[CK_TILE] Add paged-kvcache support in group mode fmha fwd splitkv kernels (#1678)

* Generate group mode paged-attn kernel

* Enable paged-kvcache + group mode support

* Add missing header: fused_moe.hpp

* Add comment to explain kernel arg usage

* Make error message more clear

* Add comment for confusing data member names

* Add more comment for confusing variable names

* Fix typo in option description
This commit is contained in:
Po Yen Chen
2024-11-21 14:53:10 +08:00
committed by GitHub
parent 6916d8cc03
commit fb1ccfa9df
6 changed files with 95 additions and 43 deletions

View File

@@ -0,0 +1,11 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
#include "ck_tile/ops/fused_moe/kernel/moe_sorting_kernel.hpp"
#include "ck_tile/ops/fused_moe/pipeline/moe_sorting_pipeline.hpp"
#include "ck_tile/ops/fused_moe/pipeline/moe_sorting_policy.hpp"
#include "ck_tile/ops/fused_moe/pipeline/moe_sorting_problem.hpp"
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
#include "ck_tile/ops/common/tensor_layout.hpp"