Skip to content

Releases: NVIDIA/cutlass

CUTLASS 1.1

28 Sep 20:02
6877595
Compare
Choose a tag to compare

CUTLASS 1.1.0 release adds:

  • Documentation
  • Examples
  • Turing Features
  • Batched Strided GEMM
  • Threadblock rasterization strategies
  • Extended CUTLASS Core components
  • Enhanced CUTLASS utilities

CUTLASS 1.0.1

26 Jun 21:00
cf0301e
Compare
Choose a tag to compare

CUTLASS 1.0.1.

Intra-threadblock reduction added for small threadblock tile sizes

  • sgemm_64x128x16, sgemm_128x128x16, sgemm_128x64x16, sgemm_128x32x16, sgemm_64x64x16, sgemm_64x32x16
  • igemm_32x32x128
  • GEMM K residue handled during prologue prior to mainloop

Replaced Google Test copy with submodule. Use git submodule init

CUTLASS 1.0.0

16 May 20:47
6f0d271
Compare
Choose a tag to compare

CUTLASS v1.0.0

CUTLASS 0.1.1

16 May 20:46
8437724
Compare
Choose a tag to compare

Final patch of CUTLASS v0.1.

CUTLASS 0.1.0

05 Dec 20:49
Compare
Choose a tag to compare

CUTLASS initial release.