Revert "[Perf][1/N] w8a8c8 support in dsv3.2/glm5 (#7029)" (#7288)

### What this PR does / why we need it?
This reverts commit 7ed9e9de69, which
introduces an issue that the patch doesn't work with recompute scheduler
enabled.
- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2026-03-15 20:19:09 +08:00
committed by GitHub
parent 29f195a91c
commit 0c299f79b9
24 changed files with 79 additions and 4281 deletions

View File

@@ -1,41 +0,0 @@
# 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 LightningIndexerQuant
OPTIONS --cce-auto-sync=off
-Wno-deprecated-declarations
-Werror
-mllvm -cce-aicore-hoist-movemask=false
--op_relocatable_kernel_binary=true
)
set(lightning_indexer_quant_depends transformer/attention/lightning_indexer_quant PARENT_SCOPE)
target_sources(op_host_aclnn PRIVATE
lightning_indexer_quant_def.cpp
)
target_sources(optiling PRIVATE
lightning_indexer_quant_tiling.cpp
)
if (NOT BUILD_OPEN_PROJECT)
target_sources(opmaster_ct PRIVATE
lightning_indexer_quant_tiling.cpp
)
endif ()
target_include_directories(optiling PRIVATE
${CMAKE_CURRENT_SOURCE_DIR}/op_host
)
target_sources(opsproto PRIVATE
lightning_indexer_quant_proto.cpp
)