mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
9f9edd783c
* refactor: Move executor recv functions into classes Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Enhance MPI logging and error handling - Updated MPI logging to include destination and tag information for better traceability during send and receive operations. - Added error checking for MPI_Wait and MPI_Cancel calls to ensure proper handling of multi-device requests. - Improved code structure for clarity and maintainability. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Introduce MpiTag enumeration and update MPI function signatures - Added a new header file `mpiTags.h` to define an enumeration for MPI tags, improving code readability and maintainability. - Updated function signatures in `mpiUtils.h` and `mpiUtils.cpp` to use the new `MpiTag` type instead of raw integers for tags. - Refactored various MPI calls across the codebase to utilize the new `MpiTag` enumeration, enhancing type safety and clarity. - Removed redundant MPI tag constants from several classes, streamlining the code. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fixup! refactor: Introduce MpiTag enumeration and update MPI function signatures Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Rename tags for consistency Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
59 lines
2.0 KiB
C++
59 lines
2.0 KiB
C++
/*
|
|
* SPDX-FileCopyrightText: Copyright (c) 2025 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
|
|
|
|
#include "tensorrt_llm/batch_manager/common.h"
|
|
#include "tensorrt_llm/executor/executor.h"
|
|
#include "tensorrt_llm/runtime/common.h"
|
|
#include "tensorrt_llm/runtime/iTensor.h"
|
|
#include "tensorrt_llm/runtime/modelConfig.h"
|
|
|
|
#include <memory>
|
|
#include <optional>
|
|
|
|
namespace tensorrt_llm::batch_manager
|
|
{
|
|
namespace kv_cache_manager
|
|
{
|
|
class BaseKVCacheManager;
|
|
} // namespace kv_cache_manager
|
|
|
|
class SequenceSlotManager;
|
|
class BasePeftCacheManager;
|
|
class GenerateRequestOptions;
|
|
} // namespace tensorrt_llm::batch_manager
|
|
|
|
namespace tensorrt_llm::executor
|
|
{
|
|
struct SpeculativeDecodingFastLogitsInfo;
|
|
} // namespace tensorrt_llm::executor
|
|
|
|
namespace tensorrt_llm::batch_manager::utils
|
|
{
|
|
|
|
void draftModelSendLogitsThread(int device, std::atomic<bool>* draftModelThreadShouldExit,
|
|
RequestVector* draftRequestsWaitingToSendLogits, std::shared_ptr<SequenceSlotManager> seqSlotManager,
|
|
runtime::SizeType32 maxInputLen, std::shared_ptr<kv_cache_manager::BaseKVCacheManager> kvCacheManager,
|
|
std::shared_ptr<kv_cache_manager::BaseKVCacheManager> crossKvCacheManager,
|
|
std::shared_ptr<BasePeftCacheManager> peftCacheManager);
|
|
|
|
std::optional<runtime::ITensor::SharedPtr> targetModelReceiveLogits(
|
|
executor::SpeculativeDecodingFastLogitsInfo const& fastLogitsInfo, runtime::ModelConfig const& modelConfig);
|
|
|
|
} // namespace tensorrt_llm::batch_manager::utils
|