mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
72057a0a64
* disable overlap in encoder Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: invokeGatherBatch Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: overlap same batch Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: add enableTrtOverlap to ExecutorConfig Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * disable overlap for beam search and spec decode Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * skip overlap tests with beam search or speculative decoding Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * moveFinishedContextRequestsToGeneration and skip unfinished requests in updateRequests Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * enable overlap in GptChunkedLongContextTests Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Enable overlap in gptManagerBenchmark Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Improve early exit Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Use OptionalRef for newOutputTokens tensor Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Add overlap scheduling support to TRTLLMDecoder - Updated TRTLLMDecoder to accept an `enable_overlap_scheduler` parameter. - Modified the decoder's internal logic to utilize the overlap scheduling feature. - Adjusted the sequence lengths handling to ensure compatibility with the new scheduling approach. - Enhanced unit tests to include cases for the overlap scheduler with the TRTLLMDecoder. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fix: allNewTokens in PP Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
48 lines
1.7 KiB
C++
48 lines
1.7 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.
|
|
*/
|
|
|
|
#include "tensorrt_llm/executor/executor.h"
|
|
|
|
namespace tensorrt_llm::executor
|
|
{
|
|
|
|
OutputConfig::OutputConfig(bool inReturnLogProbs, bool inReturnContextLogits, bool inReturnGenerationLogits,
|
|
bool inExcludeInputFromOutput, bool inReturnEncoderOutput, bool inReturnPerfMetrics,
|
|
std::optional<std::vector<AdditionalModelOutput>> additionalModelOutputs)
|
|
: returnLogProbs(inReturnLogProbs)
|
|
, returnContextLogits(inReturnContextLogits)
|
|
, returnGenerationLogits(inReturnGenerationLogits)
|
|
, excludeInputFromOutput(inExcludeInputFromOutput)
|
|
, returnEncoderOutput(inReturnEncoderOutput)
|
|
, returnPerfMetrics(inReturnPerfMetrics)
|
|
, additionalModelOutputs(std::move(additionalModelOutputs))
|
|
{
|
|
}
|
|
|
|
AdditionalModelOutput::AdditionalModelOutput(std::string name, bool gatherContext)
|
|
: name(std::move(name))
|
|
, gatherContext(gatherContext)
|
|
{
|
|
}
|
|
|
|
bool AdditionalModelOutput::operator==(AdditionalModelOutput const& other) const
|
|
{
|
|
return name == other.name && gatherContext == other.gatherContext;
|
|
}
|
|
|
|
} // namespace tensorrt_llm::executor
|