[Mlir-commits] [mlir] [mlir][sparse] support sparsifying 2:4 block sparsity (PR #71749)

[Yin Tong]

Ag-Cu wrote:

Hi, recently I have been very interested in MLIR's support for NVIDIA's sparse tensor core. I saw your recent commits and wanted to ask——have MLIR only added support for the NV_2:4 sparse format so far, or have implemented an end-to-end flow that can generate calls to the sparse tensor core via mma.sp PTX instructions?

https://github.com/llvm/llvm-project/pull/71749