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

[docs] Add additional tip for generating less kernels in blockwise (#2940)

Browse Source 
- Running without this generates a lot of kernels
- Clarified CMake configuration for selecting GEMM kernels and added details on kernel generation granularity.
This commit is contained in:
Aidan Do
2026-01-22 20:53:51 -08:00
committed by GitHub
parent 667446a9dd
commit 431d070fcb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/81_blackwell_gemm_blockwise/README.md
View File

@@ -50,7 +50,7 @@ To determine the most performance Blockwise/Groupwise GEMM or Grouped GEMM kerne
All Blockwise/Groupwise GEMMs and Group GEMMs with `f32` scaling of `e4m3` or runtime `f8` types can be selected by
selecting a subset of kernels when configuring with CMake by passing:
`-DCUTLASS_LIBRARY_KERNELS="cutlass3x*f32xe4m3_*f32xe4m3*,cutlass3x*f32xf8_*f32xf8*"`.
`-DCUTLASS_LIBRARY_KERNELS="cutlass3x*f32xe4m3_*f32xe4m3*,cutlass3x*f32xf8_*f32xf8*"` (you can further reduce the amount of kernels generated by specifying the SFA and SFB scale granularities e.g., `cutlass3x*1x128f32xe4m3_*128x128f32xe4m3*`).
The simplest way to use the profiler is to pass `m`, `n`, and `k` as well as your `scale_vec_size_m`,
`scale_vec_size_n`, and `scale_vec_size_k`. Passing `enable-best-kernel-for-fixed-shape` will do some autotuning