File tree
5,403 files changed
+0
-1427978
lines changed- .github
- ISSUE_TEMPLATE
- workflows
- CUDA-Optimized/FastSpeech
- fastspeech
- dataset
- hparams
- inferencer
- model
- text_norm
- trainer
- trt
- plugins
- add_pos_enc
- repeat
- samples_fp16
- samples
- utils
- materials
- samples
- scripts
- docker
- tacotron2
- waveglow
- DGLPyTorch/DrugDiscovery/SE3Transformer
- images
- scripts
- se3_transformer
- data_loading
- model
- layers
- runtime
- tests
- FasterTransformer
- JAX
- Classification
- ViT
- LanguageModeling
- PAXML
- T5X
- MultiModal/Imagen
- Kaldi/SpeechRecognition
- kaldi-asr-backend
- kaldi-asr-client
- model-repo/kaldi_online
- notebooks
- scripts
- docker
- MxNet/Classification/RN50v1.5
- img
- scripts
- PaddlePaddle
- Classification/RN50v1.5
- img
- models
- scripts
- inference
- training
- utils
- LanguageModeling/BERT
- bert_configs
- data
- squad
- images
- scripts
- configs
- docker
- utils
- vocab
- PyTorch
- Classification
- ConvNets
- efficientnet
- img
- inference
- AMP
- FP32
- TF32
- quantization
- training
- AMP
- FP32
- TF32
- image_classification
- models
- img
- resnet50v1.5
- img
- training
- AMP
- FP32
- TF32
- resnext101-32x4d
- img
- training
- AMP
- FP32
- TF32
- scripts
- se-resnext101-32x4d
- img
- training
- AMP
- FP32
- TF32
- triton
- deployment_toolkit
- library
- resnet50
- plots
- resnext101-32x4d
- scripts
- docker
- se-resnext101-32x4d
- GPUNet
- configs
- batch1/GV100
- figs
- models
- train_params
- triton
- 05ms-D
- reports
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots
- runner
- 065ms
- reports
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots
- runner
- 085ms
- reports
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots
- runner
- 08ms-D
- reports
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots
- runner
- 125ms-D
- reports
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots
- runner
- 175ms
- reports
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots
- runner
- 225ms-D
- reports
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_2_triton_performance_online_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_offline_2/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_2_triton_performance_online_2/plots
- runner
- deployment_toolkit
- library
- triton_inference_runner
- triton_performance_runner
- model_analyzer
- perf_analyzer
- runner
- maintainer
- docker
- containers
- scripts
- docker
- img
- Detection
- Efficientdet
- data
- effdet
- config
- csrc
- focal_loss
- nms
- cpu
- cuda
- layers
- object_detection
- img
- scripts
- D0
- docker
- waymo
- utils
- waymo_tool
- SSD
- dle
- examples
- img
- ssd
- img
- DrugDiscovery
- MoFlow
- img
- moflow
- data
- model
- runtime
- scripts
- SE3Transformer
- Forecasting/TFT
- scripts
- triton
- deployment_toolkit
- bermuda
- model_analyzer
- perf_analyzer
- reports
- nvidia_a30_experiment_17_triton_performance_offline_17/plots
- nvidia_a30_experiment_17_triton_performance_online_17/plots
- nvidia_a30_experiment_18_triton_performance_offline_18/plots
- nvidia_a30_experiment_18_triton_performance_online_18/plots
- nvidia_a30_experiment_27_triton_performance_offline_27/plots
- nvidia_a30_experiment_27_triton_performance_online_27/plots
- nvidia_a30_experiment_28_triton_performance_offline_28/plots
- nvidia_a30_experiment_28_triton_performance_online_28/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_17_triton_performance_offline_17/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_17_triton_performance_online_17/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_18_triton_performance_offline_18/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_18_triton_performance_online_18/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_27_triton_performance_offline_27/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_27_triton_performance_online_27/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_28_triton_performance_offline_28/plots
- nvidia_dgx-1_(1x_v100_32gb)_experiment_28_triton_performance_online_28/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_17_triton_performance_offline_17/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_17_triton_performance_online_17/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_18_triton_performance_offline_18/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_18_triton_performance_online_18/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_27_triton_performance_offline_27/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_27_triton_performance_online_27/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_28_triton_performance_offline_28/plots
- nvidia_dgx_a100_(1x_a100_80gb)_experiment_28_triton_performance_online_28/plots
- nvidia_t4_experiment_17_triton_performance_offline_17/plots
- nvidia_t4_experiment_17_triton_performance_online_17/plots
- nvidia_t4_experiment_18_triton_performance_offline_18/plots
- nvidia_t4_experiment_18_triton_performance_online_18/plots
- nvidia_t4_experiment_27_triton_performance_offline_27/plots
- nvidia_t4_experiment_27_triton_performance_online_27/plots
- nvidia_t4_experiment_28_triton_performance_offline_28/plots
- nvidia_t4_experiment_28_triton_performance_online_28/plots
- runner
- maintainer
- docker
- containers
- scripts
- docker
- LanguageModeling
- BART
- bart
- configuration
- modeling
- tokenization
- configs
- images
- scripts
- docker
- params
- utils
- BERT
- bert_configs
- checkpoints
- data
- squad
- distillation
- BERT_4L_288D
- BERT_4L_312D
- BERT_6L_768D
- utils
- squad
- images
- lamb_amp_opt
- csrc
- fused_lamb
- processors
- results
- scripts
- configs
- docker
- triton
- deployment_toolkit
- bermuda
- model_analyzer
- perf_analyzer
- dist4l
- runner
- scripts
- docker
- dist6l
- runner
- scripts
- docker
- large
- runner
- scripts
- docker
- runner
- maintainer
- docker
- containers
- vocab
- Transformer-XL
- pytorch
- img
- inference
- scripts
- docker
- tests
- utils
- Recommendation
- DLRM
- dlrm
- cuda_ext
- cuda_src
- dot_based_interact_ampere
- dot_based_interact_volta
- dot_based_interact
- sparse_gather
- data
- model
- nn
- scripts
- utils
- checkpointing
- img
- notebooks
- preproc
- gpu
- tests
- feature_specs
- transcoding
- triton
- img
- NCF
- data
- csv_conversion
- like_movielens
- ml-20m
- img
- qa
- Segmentation
- MaskRCNN
- img
- pytorch
- configs
- caffe2
- cityscapes
- ci
- gn_baselines
- pascal_voc
- quick_schedules
- demo
- docker
- docker-jupyter
- maskrcnn_benchmark
- config
- csrc
- cpu
- cuda
- data
- datasets
- evaluation
- coco
- voc
- samplers
- transforms
- engine
- layers
- modeling
- backbone
- detector
- roi_heads
- box_head
- mask_head
- rpn
- solver
- structures
- utils
- notebooks
- scripts
- docker
- tests
- tools
- cityscapes
- img
- nnUNet
- data_loading
- data_preprocessing
- images
- nnunet
- notebooks
- scripts
- triton
- deployment_toolkit
- bermuda
- plots
- scripts
- docker
- utils
- SpeechRecognition
- Jasper
- common
- dali
- text
- unidecoder
- configs
- images
- jasper
- notebooks
- platform
- scripts
- docker
- triton
- model_repo_configs
- fp16
- decoder-ts-script
- feature-extractor-ts-trace
- jasper-onnx-ensemble
- jasper-onnx
- jasper-tensorrt-ensemble
- jasper-tensorrt
- jasper-ts-trace-ensemble
- jasper-ts-trace
- fp32
- decoder-ts-script
- feature-extractor-ts-trace
- jasper-onnx-ensemble
- jasper-onnx
- jasper-tensorrt-ensemble
- jasper-tensorrt
- jasper-ts-trace-ensemble
- jasper-ts-trace
- pytorch
- scripts
- docker
- utils
- QuartzNet
- common
- dali
- text
- unidecoder
- configs
- img
- platform
- quartznet
- scripts
- docker
- utils
- img
- wav2vec2
- common
- fairseq
- data
- audio
- modules
- optim
- img
- scripts
- docker
- utils
- wav2vec2
- SpeechSynthesis
- FastPitch
- audio
- cmudict
- common
- text
- unidecoder
- zh
- fastpitch
- filelists
- hifigan
- img
- notebooks
- phrases
- platform
- scripts
- docker
- mandarin_chinese
- triton
- deployment_toolkit
- bermuda
- plots
- scripts
- docker
- waveglow
- HiFiGAN
- audio
- common
- text
- unidecoder
- data
- cmudict
- filelists
- fastpitch
- hifigan
- img
- platform
- scripts
- docker
- Tacotron2
- audio
- data
- exports
- filelists
- img
- notebooks
- conversationalai
- client
- speech_ai_demo
- utils
- bert
- jasper
- tacotron2
- unidecoder
- model_preparation
- model_repo
- bert-onnx
- bertQA-ts-script
- jasper-decoder
- jasper-feature-extractor
- jasper-trt-ensemble
- jasper-trt
- tacotron2
- waveglow-trt
- triton
- phrases
- platform
- scripts
- docker
- tacotron2_common
- tacotron2
- text
- unidecoder
- tensorrt
- trtis_cpp
- model-config/tacotron2waveglow
- scripts
- import_utils
- src
- bin
- test
- trtis
- trt
- common
- data
- denoiser
- layers
- plugins
- taco2AttentionPlugin
- taco2DenoiseTransformPlugin
- taco2LSTMCellPlugin
- taco2ModulationRemovalPlugin
- taco2PrenetPlugin
- taco2ProjectionPlugin
- tacotron2
- util
- waveglow
- trtis_client
- src
- bin
- waveglow
- img
- Translation
- GNMT
- img
- scripts
- docker
- tests
- seq2seq
- data
- inference
- models
- train
- Transformer
- examples
- translation
- fairseq
- data
- csrc
- models
- modules
- strided_batched_gemm
- optim
- lr_scheduler
- prefixes
- scripts
- img
- TensorFlow
- Classification
- ConvNets
- dataprep
- model
- blocks
- layers
- resnet50v1.5
- imgs
- training
- resnext101-32x4d
- imgs
- training
- runtime
- se-resnext101-32x4d
- imgs
- training
- triton
- deployment_toolkit
- library
- plots
- scripts
- docker
- utils
- hooks
- img
- Detection
- SSD
- configs
- examples
- img
- models
- research/object_detection
Some content is hidden
Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
5,403 files changed
+0
-1427978
lines changedThis file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
0 commit comments