add links of other readme in the master readme (#70)

* add links of other readme in the master readme

* modify links of training/inference readme

* modify links of training/inference readme

Author: godweiyang

README.md

@@ -11,8 +11,8 @@ LightSeq is a high performance training and inference library for sequence proce
 in CUDA.
 It enables highly efficient computation of modern NLP models such as **BERT**, **GPT**,
 **Transformer**, etc.
-It is therefore best useful for Machine Translation, *Text Generation*, *Dialog*, *Language
-Modelling*, *Sentiment analysis*, and other related tasks with sequence data.
+It is therefore best useful for *Machine Translation*, *Text Generation*, *Dialog*, *Language
+Modelling*, *Sentiment Analysis*, and other related tasks with sequence data.
 
 The library is built on top of CUDA official
 library([cuBLAS](https://docs.nvidia.com/cuda/cublas/index.html),
@@ -23,11 +23,14 @@ addition to model components, the inference library also provide easy-to deploy
 Server](https://docs.nvidia.com/deeplearning/sdk/inference-server-archived/tensorrt_inference_server_120/tensorrt-inference-server-guide/docs/quickstart.html).
 With LightSeq, one can easily develop modified Transformer architecture with little additional code.
 
+## Features
+### [Training](./lightseq/training)
 The following is a support matrix of LightSeq **training** library compared with
 [DeepSpeed](https://github.com/microsoft/DeepSpeed).
 
 ![features](./docs/training/images/features.png)
 
+### [Inference](./lightseq/inference)
 The following is a support matrix of LightSeq **inference** library compared with
 [TurboTransformers](https://github.com/Tencent/TurboTransformers) and
 [FasterTransformer](https://github.com/NVIDIA/DeepLearningExamples/tree/master/FasterTransformer).
@@ -37,7 +40,7 @@ The following is a support matrix of LightSeq **inference** library compared wit
 
 ## Performance
 
-### Training
+### [Training](./lightseq/training)
 Here we present the experimental results on WMT14 English to German translation task based on Transformer-big models. We train Transformer models of different sizes on eight NVIDIA Tesla V100/NVIDIA Ampere A100 GPUs with data parallel and fp16 mixed precision.
 [Fairseq](https://github.com/pytorch/fairseq) with [Apex](https://github.com/NVIDIA/apex) is choosed as our baseline.
 
@@ -47,7 +50,7 @@ We compute speedup on different batch size using the WPS (real words per second)
 
 More results is available [here](./docs/training/performance.md)
 
-### Inference
+### [Inference](./lightseq/inference)
 Here we present the experimental results on neural machine translation based on Transformer-base models using beam search methods.
 We choose Tensorflow and
 [FasterTransformer](https://github.com/NVIDIA/DeepLearningExamples/tree/master/FasterTransformer) as a comparison.
@@ -79,6 +82,8 @@ sh examples/training/fairseq/ls_fairseq_wmt14en2de.sh
 
 To compare lightseq with fairseq, delete the arguments with `ls_`prefix to using the original fairseq implementation
 
+More usage is available [here](./lightseq/training/README.md).
+
 ### Fast inference from HuggingFace bart
 
 We provide an end2end bart-base example to see how fast Lightseq is compared to HuggingFace. First you should install these requirements.
@@ -97,14 +102,15 @@ python ls_bart.py
 
 LightSeq installation from pypi only supports python 3.6 to 3.8 on Linux for now. Consider compiling from source if you have other environments.
 
+More usage is available [here](./lightseq/inference/README.md).
 
 ## Cite Us
 
 If you use LightSeq in your research, please cite the following paper.
 
 ```
 @InProceedings{wang2021lightseq,
-  title = "{L}ight{S}eq: A High Performance Inference Library for Transformers",
+    title = "{L}ight{S}eq: A High Performance Inference Library for Transformers",
     author = "Wang, Xiaohui and Xiong, Ying and Wei, Yang and Wang, Mingxuan and Li, Lei",
     booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers (NAACL-HLT)",
     month = jun,
@@ -117,4 +123,4 @@ If you use LightSeq in your research, please cite the following paper.
 ## Contact
 
 Any questions or suggestions, please feel free to contact us at
-wangxiaohui.neo@bytedance.com, xiongying.taka@bytedance.com, weiyang.god@bytedance.com, wangmingxuan.89@bytedance.com, lileilab@bytedance.com
+wangxiaohui.neo@bytedance.com, xiongying.taka@bytedance.com, qian.xian@bytedance.com, weiyang.god@bytedance.com, wangmingxuan.89@bytedance.com, lileilab@bytedance.com