Sean Silva
Great! @ashay, I couldn't find a good tool on github to manage rotations like this -- do you know of any? If not, as a low-tech solution, could you maybe...
> Here's the list: https://github.com/llvm/torch-mlir/wiki/Weekly-LLVM-Update. Feel free to edit as you see fit. I'll be sure to cc the listed person when I post the LLVM green commit. Thanks all!...
I'd like to avoid having yet another file that needs to be updated as we add ops. Is the build time savings massive from this? I think once we have...
Can we close this? #1384 landed.
@powderluv here's something that should allow you to move forward with large weights. Still lots to do downstream from Torch-MLIR though (IREE etc.)
Is this actually a core issue about how we want to model mhlo.reduce going forward, or is this more about the mechanics of lowering to linalg? It feels like lowing...
In this particular case, the root cause seems to be the upstream LLVM patch and I do not see an immediate need to change our policy. That patch breaks existing...
I think the longer-term path here is to use TorchDynamo which eliminates the need for this patch altogether except for AoT use cases. The AoT use cases are a more...
Closed in favor of https://github.com/llvm/torch-mlir/pull/1793