mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
20d0649f19
Signed-off-by: Yao Yao <lowsfer@users.noreply.github.com> Signed-off-by: peaceh <103117813+peaceh-nv@users.noreply.github.com> Signed-off-by: Jinyang Yuan <154768711+jinyangyuan-nvidia@users.noreply.github.com> Co-authored-by: Yao Yao <lowsfer@users.noreply.github.com> Co-authored-by: peaceh-nv <103117813+peaceh-nv@users.noreply.github.com>
36 lines
1.3 KiB
C++
36 lines
1.3 KiB
C++
/*
|
|
* Copyright (c) 2020-2023, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
#pragma once
|
|
#include "tensorrt_llm/kernels/decoderMaskedMultiheadAttention/xqaParams.h"
|
|
#include "tensorrt_llm/kernels/trtllmGenKernels/fmha/fmhaRunner.h"
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
namespace jit
|
|
{
|
|
|
|
bool supportConfigQGMMA(XQAParams const& xqaParams, int SM, bool forConfigurePlugin);
|
|
bool supportConfigHMMA(XQAParams const& xqaParams, int SM, bool forConfigurePlugin);
|
|
bool supportConfigMLA(XQAParams const& xqaParams, int SM, bool forConfigurePlugin);
|
|
bool supportConfigTllmGen(
|
|
XQAParams const& xqaParams, int SM, bool forConfigurePlugin, TllmGenFmhaRunner const* tllmRunner);
|
|
|
|
} // namespace jit
|
|
} // namespace kernels
|
|
} // namespace tensorrt_llm
|