nvxuanyuc d1398c05e6 [None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127) ... Signed-off-by: Xuanyu Chen <xuanyuc@nvidia.com>		2025-10-27 13:12:31 -04:00
..
banWordsLayer.cpp
banWordsLayer.h
baseLayer.h
beamSearchLayer.cu
beamSearchLayer.h
CMakeLists.txt
decodingLayer.cpp
decodingLayer.h
decodingParams.h	[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)	2025-10-27 13:12:31 -04:00
dynamicDecodeLayer.cpp
dynamicDecodeLayer.h
eagleDecodingLayer.cpp
eagleDecodingLayer.h
explicitDraftTokensLayer.cpp
explicitDraftTokensLayer.h
externalDraftTokensLayer.cpp
externalDraftTokensLayer.h
layersFactory.h
layerUtils.h
lookaheadAlgorithm.cpp
lookaheadAlgorithm.h
lookaheadDecodingLayer.cpp
lookaheadDecodingLayer.h
lookaheadDecodingUtils.h
lookaheadPoolManager.cpp
lookaheadPoolManager.h
medusaDecodingLayer.cpp
medusaDecodingLayer.h
penaltyLayer.cpp	[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)	2025-10-27 13:12:31 -04:00
penaltyLayer.h	[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)	2025-10-27 13:12:31 -04:00
samplingLayer.cpp
samplingLayer.h
stopCriteriaLayer.cpp
stopCriteriaLayer.h
topKSamplingLayer.cpp
topKSamplingLayer.h
topPSamplingLayer.cpp
topPSamplingLayer.h