update BT READMEs

[HamidShojanazeri]

Description

This PR clarify the docs on the use of Flash attention and Xformer mem efficient kernels in Better Transformers/ Accelerated Transformers

Fixes #(issue)

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• New feature (non-breaking change which adds functionality)
• [ X] This change requires a documentation update

[codecov]

Codecov Report

Merging #2474 (26d1b37) into master (754c2f9) will increase coverage by 0.08%.
The diff coverage is n/a.

❗ Current head 26d1b37 differs from pull request most recent head 05fe7f3. Consider uploading reports for the commit 05fe7f3 to get more accurate results

@@            Coverage Diff             @@
##           master    #2474      +/-   ##
==========================================
+ Coverage   71.81%   71.89%   +0.08%     
==========================================
  Files          78       78              
  Lines        3654     3654              
  Branches       58       58              
==========================================
+ Hits         2624     2627       +3     
+ Misses       1026     1023       -3     
  Partials        4        4              

see 1 file with indirect coverage changes

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

[msaroufim]

Thanks @HamidShojanazeri a few minor typos here and this should be good to merge https://github.com/pytorch/serve/actions/runs/5592480108/jobs/10224980538?pr=2474#step:5:22 - stamping to unblock