youngkingdom/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md for 3.9

Browse Source
This commit is contained in:
Haicheng Wu
2025-04-24 16:51:45 -04:00
committed by GitHub
parent 331a1f5b3f
commit f02a7c2976
1 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -2,7 +2,7 @@
# CUTLASS 3.9.0
_CUTLASS 3.9.0 - March 2025_
_CUTLASS 3.9.0 - April 2025_
CUTLASS is a collection of CUDA C++ template abstractions for implementing
high-performance matrix-matrix multiplication (GEMM) and related computations at all levels
@ -53,15 +53,23 @@ architecture.
- [Grouped GEMM with nvfp4 datatype](./examples/79_blackwell_geforce_gemm/79d_blackwell_geforce_nvfp4_grouped_gemm.cu).
- [Sparse Blockscaled GEMM with mxfp8 input datatype and BF16 output tensor](./examples/80_blackwell_geforce_sparse_gemm/80a_blackwell_geforce_mxfp8_bf16_sparse_gemm.cu).
- [Sparse Blockscaled GEMM with NVFP4 input datatype and NVFP4 output tensor](./examples/80_blackwell_geforce_sparse_gemm/80b_blackwell_geforce_nvfp4_nvfp4_sparse_gemm.cu).
* A new Multi-head Latent Attention (MLA) for SM100 Blackwell architecture in CUTLASS [example](./examples/77_blackwell_fmha/): both [forward](./examples/77_blackwell_fmha/77_blackwell_fmha.cu) and [backward](./examples/77_blackwell_fmha/77_blackwell_fmha_bwd.cu) passes are supported.
* A new [distributed GEMM example](./examples/82_blackwell_distributed_gemm/82_blackwell_distributed_gemm.cu) for SM100 Blackwell architecture.
* Set of unit tests that demonstrate the usage of both [sparse](./test/unit/gemm/device/sm120_blockscaled_sparse_tensorop_gemm/) and [dense](./test/unit/gemm/device/sm120_blockscaled_tensorop_gemm/) Blackwell SM120 blockscaled GEMM.
* Support for Blackwell SM100 Sparse kernels:
- Collective mainloop that target for
* [SM100 Sparse GEMM](./include/cutlass/gemm/collective/sm100_sparse_mma_warpspecialized.hpp)
* Set of example that demonstrate the usage of the 3.x API for targeting Blackwell SM100 Sparse GEMM:
- [Sparse GEMM](./examples/83_blackwell_sparse_gemm/83_blackwell_sparse_gemm.cu)
- [Blockscaled Sparse GEMM with NVFP4 input data type](./examples/84_blackwell_narrow_precision_sparse_gemm/84a_blackwell_nvfp4_bf16_sparse_gemm.cu)
- [Blockscaled Sparse GEMM with mixed input data type (MXFP8 and MXFP4)](./examples/84_blackwell_narrow_precision_sparse_gemm/84b_blackwell_mixed_mxfp8_bf16_sparse_gemm.cu)
* Set of unit tests that demonstrate the usage of [sparse](./test/unit/gemm/device/sm100_sparse_tensorop_gemm) and [blockscaled sparse](./test/unit/gemm/device/sm100_blockscaled_sparse_tensorop_gemm) Blackwell SM100 GEMM.
* A new Multi-head Latent Attention (MLA) for SM100 Blackwell architecture in CUTLASS [example](./examples/77_blackwell_fmha/) covers the flashMLA-like weight-absorbed decoding use-case.
* A new FMHA Backward kernel for SM100 Blackwell architecture extends CUTLASS [example](./examples/77_blackwell_fmha/) to show how the five backward pass MMAs can be fused into a single kernel to achieve high performance.
* A new [distributed GEMM example](./examples/82_blackwell_distributed_gemm/82_blackwell_distributed_gemm.cu) for SM100 Blackwell architecture.
* Enhancement and new support of block-wise and group-wise GEMM for Hopper and Blackwell architectures:
- Enhancement of [blockwise GEMM](./examples/67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling/67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling.cu) for Hopper architecture.
- Enhancement of [groupwise GEMM](./examples/67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling/67_hopper_fp8_warp_specialized_gemm_with_groupwise_scaling.cu) for Hopper architecture.
- Support for [grouped GEMM with blockwise and groupwise scaling](./examples/68_hopper_fp8_warp_specialized_grouped_gemm_with_blockwise_scaling/) for Hopper architecture.
- Support for [grouped-wise GEMM](./tools/profiler/src/blockwise_gemm_operation_profiler.cu) in CUTLASS profiler.
- Support for [mixed-dtype grouped GEMM with groupwise scaling](./examples/69_hopper_mixed_dtype_grouped_gemm) for Hopper architecture.
- Support for [blockwise GEMM](./examples/81_blackwell_gemm_blockwise/81_blackwell_gemm_blockwise.cu) for Blackwell architecture.
- Support for [groupwise GEMM](./examples/81_blackwell_gemm_blockwise/81_blackwell_gemm_groupwise.cu) for Blackwell architecture.
- Support for [grouped GEMM with blockwise](./examples/81_blackwell_gemm_blockwise/81_blackwell_grouped_gemm_blockwise.cu) and [groupwise scaling](./examples/81_blackwell_gemm_blockwise/81_blackwell_grouped_gemm_groupwise.cu) for Blackwell architecture.