[Mlir-commits] [mlir] [mlir][linalg] Implement `LinalgGroupedConvolutionOpInterface` to unify grouped convs (PR #94796)

[llvmlistbot at llvm.org]

srcarroll wrote:

There has been an ongoing effort by @rengolin and others to thwart the op explosion in linalg dialect. See [here](https://discourse.llvm.org/t/rfc-extend-linalg-elemwise-named-ops-semantics/83927/12) where I had a brief discussion about it. So it would help most to get initial feedback from those involved. I believe @MaheshRavishankar  and @banach-space are the relevant people to get eyes on this. Since I started this about a year ago, I'm not really sure how this fits into what they plan, so I dont want to get in the way. But if they feel this is in the right direction, then I can start working on this more

https://github.com/llvm/llvm-project/pull/94796