moe_gating_top_k (#5271)

1. What this PR does / why we need it?
This PR supports the moe_gating_top_k operator, which enables
post-positioned renormalization (renorm) on the basis of softmax.
2. Does this PR introduce any user-facing change?
No user-facing changes are required.
3. How was this patch tested?
This patch was tested with the test_npu_moe_gating_top_k test case.
vLLM version: release/v0.13.0
vLLM main:
ad32e3e19c

---------

Signed-off-by: ZCG12345 <2097562023@qq.com>
Signed-off-by: zzzzwwjj <34335947+zzzzwwjj@users.noreply.github.com>
Co-authored-by: zzzzwwjj <34335947+zzzzwwjj@users.noreply.github.com>
This commit is contained in:
ZCG12345
2025-12-30 09:28:01 +08:00
committed by GitHub
parent 15d73f248e
commit 45c3c279e2
34 changed files with 4791 additions and 22 deletions

View File

@@ -0,0 +1,30 @@
/**
 * This program is free software, you can redistribute it and/or modify.
 * 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 tiling_util.h
* \brief
*/
#pragma once
#include "register/op_impl_registry.h"
namespace Ops {
namespace Transformer {
namespace OpTiling {
bool IsRegbaseSocVersion(const gert::TilingParseContext* context);
bool IsRegbaseSocVersion(const gert::TilingContext* context);
const gert::Shape& EnsureNotScalar(const gert::Shape& inShape);
} // namespace OpTiling
} // namespace Transformer
} // namespace Ops