mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
deaae40bd7
* Update TensorRT-LLM --------- Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
29 lines
937 B
C++
29 lines
937 B
C++
/*
|
|
* SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
* SPDX-License-Identifier: Apache-2.0
|
|
*
|
|
* 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
|
|
|
|
namespace tensorrt_llm::common
|
|
{
|
|
|
|
// Tune the number of blocks per sequence for accuracy/performance purpose.
|
|
bool getEnvMmhaMultiblockDebug();
|
|
|
|
int getEnvMmhaBlocksPerSequence();
|
|
|
|
} // namespace tensorrt_llm::common
|