feature(frameworks): bentoml.onnx runner accept kwargs

[larme]

What does this PR address?

Sometimes it's more nature to call onnx model with keyword arguments. For example, bert's tokenizer will output a dictionary, which the original model will call with model(**input). Our runner should simulate this behavior

Fixes #(issue)

Before submitting:

• Does the Pull Request follow Conventional Commits specification naming? Here are GitHub's
  guide on how to create a pull request.
• Does the code follow BentoML's code style, both make format and make lint script have passed (instructions)?
• Did you read through contribution guidelines and follow development guidelines?
• Did your changes require updates to the documentation? Have you updated
  those accordingly? Here are documentation guidelines and tips on writting docs.
• Did you write tests to cover your changes?

[codecov]

Codecov Report

Merging #3561 (607ec46) into main (afe9660) will not change coverage.
The diff coverage is 0.00%.

@@          Coverage Diff          @@
##            main   #3561   +/-   ##
=====================================
  Coverage   0.00%   0.00%           
=====================================
  Files        154     154           
  Lines      12620   12632   +12     
=====================================
- Misses     12620   12632   +12     

Impacted Files	Coverage Δ
src/bentoml/_internal/frameworks/onnx.py	0.00% <0.00%> (ø)

[aarnphm]

cc @larme, I ran the test locally, it passed, but it still didn't run on CI. can you also fix it as well?

[bojiang]

Does this mean we can not call onnx_runner.run(arg1, arg2, kwarg1=xxx), using args and kwargs at same time?

[aarnphm]

no I don't think so.

[sauyon]

Yes, it does.

[larme]

For every onnx model we have a fixed list of inputs with their own names. Calling by args means refer each argument by its position while calling by kwargs means refer each argument by its name. Now if we mix these 2 methods, I feel that it's very easy for user to miss some arguments.

Calling by kwargs is useful when dealing with NLP models where the tokenizer output a dictionary and the dictionary is passed to the model as kwargs. In this use case there's no additional positional argument to be passed

[aarnphm]

Do we need more discussion about this?

[larme]

let's have a discussion on engineer meeting

[larme]

@aarnphm Now the tests run on CI. The problem is that the new bert tests will missing the pytorch dependencies (I thought installing transformers will install torch by default, I was wrong).

[sauyon]

@larme @aarnphm what's the status of this one?

[aarnphm]

This has been on this list for a while now @larme we should circle back and get this one merge