EngineX-Ascend/enginex-ascend-910-vllm
11
0
Fork 1
Code Issues Pull Requests Actions Projects Releases Wiki Activity

init v0.23.0

Browse Source 
Signed-off-by: Sun Ruoxi <sunruoxi@4paradigm.com>
This commit is contained in:
Sun Ruoxi
2026-08-27 15:11:51 +08:00
parent b582a8e7d1
commit 7f8a1b1f7a
2849 changed files with 712887 additions and 22001 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
csrc/moe/causal_conv1d/op_kernel/causal_conv1d_update.h Normal file
View File

@@ -0,0 +1,91 @@
/**
* 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.
*/
#ifndef CAUSAL_CONV1D_UPDATE_H
#define CAUSAL_CONV1D_UPDATE_H
#include "causal_conv1d.h"
namespace NsCausalConv1d {
template <typename T>
class CausalConv1dUpdate
: public CausalConv1d<T, CAUSAL_CONV1D_TPL_RUN_MODE_UPDATE, CAUSAL_CONV1D_TPL_WIDTH_RUNTIME,
CAUSAL_CONV1D_TPL_FN_PLAN_INVALID> {
public:
__aicore__ inline void Init(GM_ADDR x, GM_ADDR weight, GM_ADDR bias, GM_ADDR convStates, GM_ADDR queryStartLoc,
GM_ADDR cacheIndices, GM_ADDR, GM_ADDR numAcceptedTokens, GM_ADDR y, GM_ADDR workspace,
const CausalConv1dTilingData *tilingData)
{
(void)workspace;
this->ResetRuntimeState(tilingData);
this->xGm.SetGlobalBuffer(reinterpret_cast<__gm__ T *>(x));
this->weightGm.SetGlobalBuffer(reinterpret_cast<__gm__ T *>(weight));
this->biasGm.SetGlobalBuffer(reinterpret_cast<__gm__ T *>(bias));
this->convStatesGm.SetGlobalBuffer(reinterpret_cast<__gm__ T *>(convStates));
if (tilingData->hasQueryStartLoc != 0) {
if (tilingData->queryStartLocUseInt64 != 0) {
this->queryStartLocGmInt64.SetGlobalBuffer(reinterpret_cast<__gm__ int64_t *>(queryStartLoc));
} else {
this->queryStartLocGmInt32.SetGlobalBuffer(reinterpret_cast<__gm__ int32_t *>(queryStartLoc));
}
}
if (tilingData->hasCacheIndices != 0) {
if (tilingData->cacheIndicesUseInt64 != 0) {
this->cacheIndicesGmInt64.SetGlobalBuffer(reinterpret_cast<__gm__ int64_t *>(cacheIndices));
} else {
this->cacheIndicesGmInt32.SetGlobalBuffer(reinterpret_cast<__gm__ int32_t *>(cacheIndices));
}
}
if (tilingData->hasNumAcceptedTokens != 0) {
if (tilingData->numAcceptedTokensUseInt64 != 0) {
this->numAcceptedTokensGmInt64.SetGlobalBuffer(reinterpret_cast<__gm__ int64_t *>(numAcceptedTokens));
} else {
this->numAcceptedTokensGmInt32.SetGlobalBuffer(reinterpret_cast<__gm__ int32_t *>(numAcceptedTokens));
}
}
this->yGm.SetGlobalBuffer(reinterpret_cast<__gm__ T *>(y));
this->InitSharedBuffersAndEvents();
}
__aicore__ inline void Process()
{
const CausalConv1dTilingData *tilingData = this->GetTilingData();
const int32_t dim = tilingData->dim;
const int32_t baseDimCnt = static_cast<int32_t>(tilingData->baseDimCnt);
const int32_t width = static_cast<int32_t>(tilingData->width);
const int32_t baseDim = static_cast<int32_t>(tilingData->baseDim);
if (baseDim <= 0 || baseDimCnt <= 0 || baseDim > MAX_BLOCK_DIM || width < 2 || width > MAX_WIDTH || dim <= 0 ||
tilingData->batch <= 0) {
this->ReleaseEvents();
return;
}
this->ProcessDefault();
this->ReleaseEvents();
}
};
template <typename T>
__aicore__ inline void RunCausalConv1dUpdate(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,
const CausalConv1dTilingData *tilingData)
{
CausalConv1dUpdate<T> op;
op.Init(x, weight, bias, convStates, queryStartLoc, cacheIndices, initialStateMode, numAcceptedTokens, y, workspace,
tilingData);
op.Process();
}
} // namespace NsCausalConv1d
#endif // CAUSAL_CONV1D_UPDATE_H