The GitHub Actions job "Lint" on tvm.git/main has failed.
Run started by GitHub user tlopex (triggered by tlopex).

Head commit for run:
1729c726bf068011fec4a921b9d1ffff5014ec12 / Ronald Nap <[email protected]>
[Relax][Frontend][ONNX] Support Modern QDQ opset attributes (#19993)

## Summary

Adds support for newer `QuantizeLinear` and `DequantizeLinear`
attributes in the Relax ONNX frontend.

This includes `output_dtype`, `saturate`, and newer opset behavior,
while rejecting unsupported blocked quantization and `precision` cases.

For `QuantizeLinear` and `DequantizeLinear`, opsets 24 and 25 use the
existing converter for currently supported types. Support for
`float8e8m0`, `int2`, and `uint2` are outside this PR’s scope.

## Testing

Added structural and rejection tests for opsets 19, 21, 23, 24, and 25.

Report URL: https://github.com/apache/tvm/actions/runs/29289063365

With regards,
GitHub Actions via GitBox


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to