Closed sdasgup3 closed 3 weeks ago
Originally brought up at https://github.com/openxla/stablehlo/pull/2383#discussion_r1630510134
The stablehlo-legalize-quant-to-int pass propagated from mho (#2383 ) uses std::variant to handle per-tensor and per-axis quantized type. However, the base class quant::QuantizedType provides a better polymorphic way to accomplish the same.
stablehlo-legalize-quant-to-int
Please review the change only in the following commit: https://github.com/openxla/stablehlo/pull/2385/commits/ee8b499fa691bbb7b6b3948bdc581dce05abaa39
Reason: This PR is based on https://github.com/openxla/stablehlo/pull/2383 which is not merged yet and hence has many files which are already reviewed as part of #2383.
Can you merge main and push? Will make reviewing a bit easier.
Originally brought up at https://github.com/openxla/stablehlo/pull/2383#discussion_r1630510134
The
stablehlo-legalize-quant-to-int
pass propagated from mho (#2383 ) uses std::variant to handle per-tensor and per-axis quantized type. However, the base class quant::QuantizedType provides a better polymorphic way to accomplish the same.Direction to reviewers
Please review the change only in the following commit: https://github.com/openxla/stablehlo/pull/2385/commits/ee8b499fa691bbb7b6b3948bdc581dce05abaa39
Reason: This PR is based on https://github.com/openxla/stablehlo/pull/2383 which is not merged yet and hence has many files which are already reviewed as part of #2383.