3 Pull requests merged by 2 people

• fix(bench): Update GEMM benchmark for compatibility with the latest codebase changes.

  #59 merged Feb 20, 2025

• fix(cell): Remove outdated code and refine implementations

  #57 merged Feb 20, 2025

• fix(cell): Support different WarpLayout in GEMMs.

  #55 merged Feb 18, 2025

1 Pull request opened by 1 person

• refactor: Enhance interfaces for SharedTile and BaseTile.

  #61 opened Feb 22, 2025

2 Issues opened by 1 person

• Optimize register utilization to improve warp occupancy rate.

  #60 opened Feb 22, 2025

• Add GEMM Benchmark with `CUTLASS` Performance Comparison.

  #56 opened Feb 18, 2025