[TVM][BUGFIX] Change graph_runtime to graph_executor & Fix MosesNormalizer

[barry-jin]

Description

TVM will deprecate graph_runtime and use graph_executor. https://github.com/apache/tvm/blob/bf862d4c4355eae4f18d89b3b6b98ed0a2c18e9c/python/tvm/contrib/graph_runtime.py#L24-L29

When building gpu docker, the log shows

Defaulting to user installation because normal site-packages is not writeable
Looking in links: https://download.pytorch.org/whl/torch_stable.html
ERROR: Could not find a version that satisfies the requirement torch==1.7.1+cu102
ERROR: No matching distribution found for torch==1.7.1+cu102

So, I changed to torch==1.8.1+cu102 @leezu
Also fix sacremoses version to <0.0.44, because the contributors of sacremoses didn't update their release for 0.0.44 on github. Updates will be tracked in #1548

Checklist

Essentials

• PR's title starts with a category (e.g. [BUGFIX], [MODEL], [TUTORIAL], [FEATURE], [DOC], etc)
• Changes are complete (i.e. I finished coding on this PR)
• All changes have test coverage
• Code is well-documented

Changes

• Feature1, tests, (and when applicable, API doc)
• Feature2, tests, (and when applicable, API doc)

Comments

• If this change is a backward incompatible change, why must this change be made.
• Interesting edge cases to note here

cc @dmlc/gluon-nlp-team

[github-actions]

The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1547/3f6d1d9cc57a909a2ed3e708cd0c4414a18e2472/index.html

[leezu]

FYI @xinyual this should fix the issue you met

[github-actions]

The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1547/d45acfce190c9dd0f7d69b7fe279249740eeafbb/index.html

[codecov]

Codecov Report

Merging #1547 (7757078) into master (1326258) will decrease coverage by 2.96%.
The diff coverage is n/a.

❗ Current head 7757078 differs from pull request most recent head d45acfc. Consider uploading reports for the commit d45acfc to get more accurate results

@@            Coverage Diff             @@
##           master    #1547      +/-   ##
==========================================
- Coverage   82.20%   79.23%   -2.97%     
==========================================
  Files          68       68              
  Lines        8540     8540              
==========================================
- Hits         7020     6767     -253     
- Misses       1520     1773     +253     

Impacted Files	Coverage Δ
setup.py	0.00% <ø> (ø)
src/gluonnlp/utils/testing.py	58.33% <0.00%> (-35.84%)	⬇️
src/gluonnlp/models/xlmr.py	58.82% <0.00%> (-29.42%)	⬇️
src/gluonnlp/models/electra.py	58.47% <0.00%> (-18.37%)	⬇️
src/gluonnlp/utils/config.py	61.53% <0.00%> (-15.39%)	⬇️
src/gluonnlp/models/bart.py	78.75% <0.00%> (-15.00%)	⬇️
src/gluonnlp/models/roberta.py	84.25% <0.00%> (-9.37%)	⬇️
src/gluonnlp/models/bert.py	87.54% <0.00%> (-7.27%)	⬇️
src/gluonnlp/models/gpt2.py	91.00% <0.00%> (-7.27%)	⬇️
src/gluonnlp/embedding/embed_loader.py	75.79% <0.00%> (-5.74%)	⬇️
... and 7 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 1326258...d45acfc. Read the comment docs.