Do not try to fold op.SplitToSequence when split is None

[titaiwangms]

split is an optional input to op.SplitToSequence.

[codecov]

Codecov Report

❌ Patch coverage is 0% with 2 lines in your changes missing coverage. Please review.
✅ Project coverage is 70.49%. Comparing base (9036fab) to head (2e86ea5).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
onnxscript/optimizer/_constant_folding.py	0.00%	1 Missing and 1 partial ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2550      +/-   ##
==========================================
+ Coverage   70.37%   70.49%   +0.11%     
==========================================
  Files         218      218              
  Lines       26428    26430       +2     
  Branches     2646     2647       +1     
==========================================
+ Hits        18600    18633      +33     
+ Misses       6922     6889      -33     
- Partials      906      908       +2     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[justinchuby]

When split is not provided it is a scalar 1. Can we use this info?

[titaiwangms]

Is it? The issue @xadupre brought up was only one input. model id: facebook/sam-vit-base, so it hit indexerror.

[justinchuby]

I think at least according to the spec: https://onnx.ai/onnx/operators/onnx__SplitToSequence.html#summary

[titaiwangms]

onnxscript/onnxscript/function_libs/torch_lib/ops/core.py

Line 8732 in cec5396

return op.SplitToSequence(self, axis=dim, keepdims=False)

[titaiwangms]

Probably came from here