[kernel] add AscendC op: lightning_indexer and sparse_flash_attention (#4625)
### What this PR does / why we need it? Provide high-performance AscendC operators lightning_indexer and sparse_flash_attention to boost the execution performance of the DeepSeek v3.2 model. Meanwhile, adapt the two AscendC operators to vllm-ascend framework. ### Does this PR introduce _any_ user-facing change? No (only underlying operator optimizations, with no user-facing changes) ### How was this patch tested? - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 Signed-off-by: MingYang119 <songmingyang@huawei.com>
This commit is contained in:
39
csrc/sparse_flash_attention/op_host/CMakeLists.txt
Normal file
39
csrc/sparse_flash_attention/op_host/CMakeLists.txt
Normal file
@@ -0,0 +1,39 @@
|
||||
# This program is free software, you can redistribute it and/or modify it.
|
||||
# Copyright (c) 2025 Huawei Technologies Co., Ltd.
|
||||
# This file is a part of the CANN Open Software.
|
||||
# Licensed under CANN Open Software License Agreement Version 2.0 (the "License").
|
||||
# Please refer to the License for details. You may not use this file except in compliance with the License.
|
||||
# THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
|
||||
# See LICENSE in the root of the software repository for the full text of the License.
|
||||
# ======================================================================================================================
|
||||
|
||||
add_ops_compile_options(
|
||||
OP_NAME SparseFlashAttention
|
||||
OPTIONS --cce-auto-sync=off
|
||||
-Wno-deprecated-declarations
|
||||
-Werror
|
||||
-fpermissive
|
||||
)
|
||||
|
||||
set(sparse_flash_attention_depends transformer/attention/sparse_flash_attention PARENT_SCOPE)
|
||||
target_sources(op_host_aclnn PRIVATE
|
||||
sparse_flash_attention_def.cpp
|
||||
)
|
||||
|
||||
target_sources(optiling PRIVATE
|
||||
sparse_flash_attention_tiling.cpp
|
||||
)
|
||||
|
||||
if (NOT BUILD_OPEN_PROJECT)
|
||||
target_sources(opmaster_ct PRIVATE
|
||||
sparse_flash_attention_tiling.cpp
|
||||
)
|
||||
endif ()
|
||||
|
||||
target_sources(opsproto PRIVATE
|
||||
sparse_flash_attention_proto.cpp
|
||||
)
|
||||
|
||||
target_include_directories(optiling PRIVATE
|
||||
${CMAKE_CURRENT_SOURCE_DIR}
|
||||
)
|
||||
Reference in New Issue
Block a user