main: - title: "Getting Started" url: /getting-started/ - title: "News" url: /news/ - title: "Tutorials" url: /tutorials/ - title: "Documentation" url: https://deepspeed.readthedocs.io/ - title: "GitHub" url: https://github.com/microsoft/DeepSpeed lnav: - title: "Feature Overview" url: /features/ - title: "Getting Started" url: /getting-started/ children: - title: "Installation" url: /getting-started/#installation - title: "Writing models" url: /getting-started/#writing-deepspeed-models - title: "Training" url: /getting-started/#training - title: "Launching" url: /getting-started/#launching-deepspeed-training - title: "Configuration" url: /docs/config-json/ children: - title: "Batch size" url: /docs/config-json/#batch-size-related-parameters - title: "Optimizer" url: /docs/config-json/#optimizer-parameters - title: "Scheduler" url: /docs/config-json/#scheduler-parameters - title: "Communication" url: /docs/config-json/#communication-options - title: "FP16" url: /docs/config-json/#fp16-training-options - title: "AMP" url: /docs/config-json/#automatic-mixed-precision-amp-training-options - title: "Gradient Clipping" url: /docs/config-json/#gradient-clipping - title: "ZeRO optimizations" url: /docs/config-json/#zero-optimizations-for-fp16-training - title: "Logging" url: /docs/config-json/#logging - title: "Flops Profiler" url: /docs/config-json/#flops-profiler - title: "Activation checkpointing" url: /docs/config-json/#activation-checkpointing - title: "Sparse Attention" url: /docs/config-json/#sparse-attention - title: "Tutorials" url: /tutorials/ children: - title: "Getting started" url: /getting-started/ - title: "Getting started on Azure" url: /tutorials/azure/ - title: "BingBertSQuAD Fine-tuning" url: /tutorials/bert-finetuning/ - title: "BERT Pre-training" url: /tutorials/bert-pretraining/ - title: "CIFAR-10" url: /tutorials/cifar-10/ - title: "Flops Profiler" url: /tutorials/flops-profiler/ - title: "GAN" url: /tutorials/gan/ - title: "Learning Rate Range Test" url: /tutorials/lrrt/ - title: "Megatron-LM GPT2" url: /tutorials/megatron/ - title: "One-Cycle Schedule" url: /tutorials/one-cycle/ - title: "One-Bit Adam" url: /tutorials/onebit-adam/ - title: "Pipeline Parallelism" url: /tutorials/pipeline/ - title: "Progressive Layer Dropping" url: /tutorials/progressive_layer_dropping/ - title: "Sparse Attention" url: /tutorials/sparse-attention/ - title: "Transformer Kernel" url: /tutorials/transformer_kernel/ - title: "ZeRO-Offload" url: /tutorials/zero-offload/ - title: "ZeRO Redundancy Optimizer (ZeRO)" url: /tutorials/zero/ - title: "Contributing" url: /contributing/