wehub-resource-sync
136 lines
4.6 KiB
YAML
Executable File
136 lines
4.6 KiB
YAML
Executable File
main:
|
|
- title: 'Getting Started'
|
|
url: /getting-started/
|
|
- title: 'Blog'
|
|
url: /posts/
|
|
- title: 'Tutorials'
|
|
url: /tutorials/
|
|
- title: 'Documentation'
|
|
url: https://deepspeed.readthedocs.io/
|
|
- title: 'GitHub'
|
|
url: https://github.com/deepspeedai/DeepSpeed
|
|
|
|
lnav:
|
|
- title: 'Training'
|
|
url: /training/
|
|
- title: 'Inference'
|
|
url: /inference/
|
|
- title: 'Compression'
|
|
url: /compression/
|
|
- title: 'Science'
|
|
url: /deepspeed4science/
|
|
- title: 'Getting Started'
|
|
url: /getting-started/
|
|
- title: 'ds_config'
|
|
url: /docs/config-json/
|
|
children:
|
|
- title: 'Autotuning'
|
|
url: /docs/config-json/#autotuning
|
|
- title: 'Batch size'
|
|
url: /docs/config-json/#batch-size-related-parameters
|
|
- title: 'Optimizer'
|
|
url: /docs/config-json/#optimizer-parameters
|
|
- title: 'FP16'
|
|
url: /docs/config-json/#fp16-training-options
|
|
- title: 'BFLOAT16'
|
|
url: /docs/config-json/#bfloat16-training-options
|
|
- 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: 'Monitoring'
|
|
url: /docs/config-json/#monitoring-module
|
|
- title: 'Communication Logging'
|
|
url: /docs/config-json/#communication-logging
|
|
- title: 'Model Compression'
|
|
url: /docs/config-json/#compression
|
|
- title: 'Data Efficiency'
|
|
url: /docs/config-json/#data-efficiency
|
|
- title: 'Tutorials'
|
|
url: /tutorials/
|
|
children:
|
|
- title: 'Getting started'
|
|
url: /getting-started/
|
|
- title: 'Getting started on Azure'
|
|
url: /tutorials/azure/
|
|
- title: 'Accelerator Abstraction'
|
|
url: /tutorials/accelerator-abstraction-interface/
|
|
- title: 'Accelerator Setup Guides'
|
|
url: /tutorials/accelerator-setup-guide/
|
|
- title: 'Automatic Tensor Parallelism (Inference)'
|
|
url: /tutorials/automatic-tensor-parallelism/
|
|
- title: 'Automatic Tensor Parallelism (Training)'
|
|
url: /tutorials/autotp-training/
|
|
- title: 'Autotuning'
|
|
url: /tutorials/autotuning/
|
|
- title: 'BingBertSQuAD Fine-tuning'
|
|
url: /tutorials/bert-finetuning/
|
|
- title: 'BERT Pre-training'
|
|
url: /tutorials/bert-pretraining/
|
|
- title: 'CIFAR-10'
|
|
url: /tutorials/cifar-10/
|
|
- title: 'Curriculum Learning'
|
|
url: /tutorials/curriculum-learning/
|
|
- title: 'Data Efficiency'
|
|
url: /tutorials/data-efficiency/
|
|
- title: 'DeepNVMe'
|
|
url: /tutorials/deepnvme/
|
|
- title: 'Domino'
|
|
url: /tutorials/domino/
|
|
- title: 'DS4Sci_EvoformerAttention'
|
|
url: /tutorials/ds4sci_evoformerattention/
|
|
- title: 'Flops Profiler'
|
|
url: /tutorials/flops-profiler/
|
|
- title: 'PyTorch Profiler'
|
|
url: /tutorials/pytorch-profiler/
|
|
- title: 'GAN'
|
|
url: /tutorials/gan/
|
|
- title: 'Inference'
|
|
url: /tutorials/inference-tutorial/
|
|
- title: 'Learning Rate Range Test'
|
|
url: /tutorials/lrrt/
|
|
- title: 'Megatron-LM GPT2'
|
|
url: /tutorials/megatron/
|
|
- title: 'Mixture of Experts (DeepSpeed MoE)'
|
|
url: /tutorials/mixture-of-experts/
|
|
- title: 'MoE for NLG'
|
|
url: /tutorials/mixture-of-experts-nlg/
|
|
- title: 'MoE Inference'
|
|
url: /tutorials/mixture-of-experts-inference/
|
|
- title: 'Model Compression'
|
|
url: /tutorials/model-compression/
|
|
- title: 'Mixture-of-Quantization'
|
|
url: /tutorials/MoQ-tutorial/
|
|
- title: 'Monitoring'
|
|
url: /tutorials/monitor
|
|
- title: 'Communication Logging'
|
|
url: /tutorials/comms-logging
|
|
- title: 'One-Cycle Schedule'
|
|
url: /tutorials/one-cycle/
|
|
- title: 'One-Bit Adam'
|
|
url: /tutorials/onebit-adam/
|
|
- title: "Zero-One Adam"
|
|
url: /tutorials/zero-one-adam/
|
|
- title: "One-Bit LAMB"
|
|
url: /tutorials/onebit-lamb/
|
|
- 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: 'Arctic Long Sequence Training (ALST) for HF Transformers integration'
|
|
url: /tutorials/ulysses-alst-sequence-parallelism
|
|
- title: 'ZeRO-Offload'
|
|
url: /tutorials/zero-offload/
|
|
- title: 'ZeRO'
|
|
url: /tutorials/zero/
|
|
- title: 'ZeRO++'
|
|
url: /tutorials/zeropp/
|
|
- title: 'Contributing'
|
|
url: /contributing/
|