554f16ae1f
### What this PR does / why we need it? This PR introduces support for adding custom CANN `aclnn` ops to `vllm-ascend`, allowing users to define and use their own custom operators. Key changes include: - Building and installing custom ops into the `vllm-ascend`-specified directory - Binding the `aclnn` op interface to the `torch.ops._C_ascend` module - Enabling invocation of these ops within `vllm-ascend` This PR includes a sample custom op: `aclnnGroupedMatmulSwigluQuantWeightNzTensorList`, which is adapted from the CANN operator [`aclnnGroupedMatmulSwigluQuantWeightNZ`](https://www.hiascend.com/document/detail/zh/canncommercial/83RC1/API/aolapi/context/aclnnGroupedMatmulSwigluQuantWeightNZ.md). Its input parameters `weight` and `weight_scale` now accept `list[torch.Tensor]` (i.e., `at::TensorList`). ### Does this PR introduce _any_ user-facing change? No. - vLLM version: v0.11.2 --------- Signed-off-by: QianChenxi <chenxi.qian.cq@outlook.com>
54 lines
1.8 KiB
C++
54 lines
1.8 KiB
C++
/**
|
|
* Copyright (c) 2024 Huawei Technologies Co., Ltd.
|
|
* This file is a part of the CANN Open Software.
|
|
* Licensed under CANN Open Software License Agreement Version 1.0 (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.
|
|
*/
|
|
|
|
/*!
|
|
* \file fallback_comm.cpp
|
|
* \brief
|
|
*/
|
|
|
|
#include "fallback_comm.h"
|
|
|
|
#include <iostream>
|
|
#include <unordered_map>
|
|
#include <vector>
|
|
#include <algorithm>
|
|
|
|
#include "aclnn/aclnn_base.h"
|
|
#include "runtime/base.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
namespace fallback {
|
|
using namespace std;
|
|
using namespace gert;
|
|
using namespace ge;
|
|
|
|
aclDataType ToAclDataType(ge::DataType dtype) {
|
|
static const std::vector<DataType> CANN_CONVERT_TO_ACL_DataType_LIST = {
|
|
ge::DataType::DT_FLOAT, ge::DataType::DT_FLOAT16, ge::DataType::DT_INT8, ge::DataType::DT_INT32,
|
|
ge::DataType::DT_UINT8, ge::DataType::DT_INT16, ge::DataType::DT_UINT16, ge::DataType::DT_UINT32,
|
|
ge::DataType::DT_INT64, ge::DataType::DT_DOUBLE, ge::DataType::DT_BOOL, ge::DataType::DT_STRING,
|
|
ge::DataType::DT_COMPLEX64, ge::DataType::DT_COMPLEX128, ge::DataType::DT_BF16, ge::DataType::DT_UINT64,
|
|
ge::DataType::DT_INT4};
|
|
auto iter = std::find(CANN_CONVERT_TO_ACL_DataType_LIST.begin(), CANN_CONVERT_TO_ACL_DataType_LIST.end(), dtype);
|
|
if (iter == CANN_CONVERT_TO_ACL_DataType_LIST.end()) {
|
|
return aclDataType::ACL_DT_UNDEFINED;
|
|
}
|
|
return static_cast<aclDataType>(dtype);
|
|
}
|
|
|
|
} // namespace fallback
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|