[Mlir-commits] [mlir] [mlir][arith] Add LUT-based lowering of arith.extf for FP8 to F32. (PR #196321)

[Jakub Kuderski]

================

----------------
kuhar wrote:

This prevents it from working with multiple fp8 types, right? Could we handle name collisions and not bail out?

https://github.com/llvm/llvm-project/pull/196321