1de805ce0a
### What this PR does / why we need it?
During the prefill phase of Qwen3-Next and Qwen3.5, the
`torch.ops._C_ascend.causal_conv1d_fn` operator exhibits significant
performance bottlenecks. To address this, we have re-implemented the
optimization using `torch.ops._C_ascend.npu_causal_conv1d_custom`.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
1 accuracy test
```
[2026-03-20 16:44:22,961] [ais_bench] [INFO] Start launch task state board ...
+-----------------------------+-----------+------------+-------------+----------+-------------------------------------------+---------------------+
| Task Name | Process | Progress | Time Cost | Status | Log Path | Extend Parameters |
+=============================+===========+============+=============+==========+===========================================+=====================+
| vllm-api-general-chat/gsm8k | 2918978 | NA | 0:00:01 | finish | logs/eval/vllm-api-general-chat/gsm8k.out | None |
+-----------------------------+-----------+------------+-------------+----------+-------------------------------------------+---------------------+
[2026-03-20 16:44:34,284] [ais_bench] [INFO] Evaluation tasks completed.
[2026-03-20 16:44:34,287] [ais_bench] [INFO] Summarizing evaluation results...
dataset version metric mode vllm-api-general-chat
--------- --------- -------- ------ -----------------------
gsm8k 271d0b accuracy gen 96.21
```
2 ut modify test
`pytest -sv
/home/c30006096/vllm-ascend/tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_causal_conv1d.py::test_ascend_causal_conv1d`
- vLLM version: v0.17.0
- vLLM main:
8b6325758c
Signed-off-by: wenba0 <3054239545@qq.com>
Signed-off-by: jiaojiao <56385650+wenba0@users.noreply.github.com>
59 lines
2.7 KiB
C++
59 lines
2.7 KiB
C++
/**
|
|
* 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.
|
|
*/
|
|
|
|
/*!
|
|
* \file causal_conv1d.cpp
|
|
* \brief
|
|
*/
|
|
|
|
#include "causal_conv1d.h"
|
|
|
|
namespace {
|
|
|
|
// NOTE:
|
|
// Dtype is provided via AscendC compile macros (e.g. DTYPE_X / ORIG_DTYPE_X), so tiling key does not need to carry dtype.
|
|
|
|
template <typename T>
|
|
__aicore__ inline void RunCausalConv1d(GM_ADDR x, GM_ADDR weight, GM_ADDR bias, GM_ADDR convStates,
|
|
GM_ADDR queryStartLoc, GM_ADDR cacheIndices, GM_ADDR initialStateMode,
|
|
GM_ADDR numAcceptedTokens, GM_ADDR y, const CausalConv1dTilingData* tilingData)
|
|
{
|
|
NsCausalConv1d::CausalConv1d<T> op;
|
|
op.Init(x, weight, bias, convStates, queryStartLoc, cacheIndices, initialStateMode, numAcceptedTokens, y, tilingData);
|
|
op.Process();
|
|
}
|
|
|
|
} // namespace
|
|
|
|
template <uint32_t schMode>
|
|
__global__ __aicore__ void causal_conv1d(GM_ADDR x, GM_ADDR weight, GM_ADDR bias, GM_ADDR convStates,
|
|
GM_ADDR queryStartLoc, GM_ADDR cacheIndices, GM_ADDR initialStateMode,
|
|
GM_ADDR numAcceptedTokens, GM_ADDR y, GM_ADDR workspace, GM_ADDR tiling)
|
|
{
|
|
REGISTER_TILING_DEFAULT(CausalConv1dTilingData);
|
|
GET_TILING_DATA_WITH_STRUCT(CausalConv1dTilingData, tilingData, tiling);
|
|
|
|
#if defined(ORIG_DTYPE_X)
|
|
#if (ORIG_DTYPE_X == DT_FLOAT16)
|
|
RunCausalConv1d<half>(x, weight, bias, convStates, queryStartLoc, cacheIndices, initialStateMode, numAcceptedTokens, y, &tilingData);
|
|
#elif (ORIG_DTYPE_X == DT_BF16)
|
|
RunCausalConv1d<bfloat16_t>(x, weight, bias, convStates, queryStartLoc, cacheIndices, initialStateMode, numAcceptedTokens, y, &tilingData);
|
|
#endif
|
|
#else
|
|
#if (DTYPE_X == DT_FLOAT16)
|
|
RunCausalConv1d<half>(x, weight, bias, convStates, queryStartLoc, cacheIndices, initialStateMode, numAcceptedTokens, y, &tilingData);
|
|
#elif (DTYPE_X == DT_BF16)
|
|
RunCausalConv1d<bfloat16_t>(x, weight, bias, convStates, queryStartLoc, cacheIndices, initialStateMode, numAcceptedTokens, y, &tilingData);
|
|
#endif
|
|
#endif
|
|
}
|
|
|