[pytorch] Add macOS M1 chip support.

[frankfliu]

Change-Id: I5fb7f2bc1ba07626fb8dcc45e1daf77d4b31765b

Description

Brief description of what this PR is about

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

[codecov-commenter]

Codecov Report

Merging #1656 (d5e7424) into master (bb5073f) will decrease coverage by 1.25%.
The diff coverage is 61.74%.

@@             Coverage Diff              @@
##             master    #1656      +/-   ##
============================================
- Coverage     72.08%   70.83%   -1.26%     
- Complexity     5126     5435     +309     
============================================
  Files           473      507      +34     
  Lines         21970    23786    +1816     
  Branches       2351     2590     +239     
============================================
+ Hits          15838    16849    +1011     
- Misses         4925     5640     +715     
- Partials       1207     1297      +90     

Impacted Files	Coverage Δ
api/src/main/java/ai/djl/modality/cv/Image.java	69.23% <ø> (-4.11%)	⬇️
...rc/main/java/ai/djl/modality/cv/output/Joints.java	71.42% <ø> (ø)
.../main/java/ai/djl/modality/cv/output/Landmark.java	100.00% <ø> (ø)
...main/java/ai/djl/modality/cv/output/Rectangle.java	72.41% <ø> (ø)
...i/djl/modality/cv/translator/BigGANTranslator.java	21.42% <ø> (-5.24%)	⬇️
...odality/cv/translator/BigGANTranslatorFactory.java	33.33% <0.00%> (+8.33%)	⬆️
...nslator/InstanceSegmentationTranslatorFactory.java	14.28% <0.00%> (-3.90%)	⬇️
.../modality/cv/translator/YoloTranslatorFactory.java	8.33% <0.00%> (-1.67%)	⬇️
...i/djl/modality/cv/translator/YoloV5Translator.java	5.69% <0.00%> (ø)
...odality/cv/translator/YoloV5TranslatorFactory.java	8.33% <0.00%> (-1.67%)	⬇️
... and 244 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 9d12c04...d5e7424. Read the comment docs.

[lanking520]

@frankfliu where do you find the binary and have you include this into our build pipeline?

[frankfliu]

I got the binary from pip wheel. There is no M1 machine we can use for CI, we have to manually build the JNI.

[lanking520]

@frankfliu do we need special build instruction for M1 chip machine? Or it is the same for us to build on Intel chip?