[Mlir-commits] [mlir] [MLIR][Linalg] Fix winograd op lowering for types smaller than f32 (PR #158500)

[Isaac Nudelman]

nuudlman wrote:

Thanks for this, I tried to figure out how to emit f16 attributes and failed. Will update to do this instead.

https://github.com/llvm/llvm-project/pull/158500