leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 24 Packages Projects Releases Wiki Activity

v4.2 release. (#2587)

Browse Source 
* Fix default cluster callback values to 1 to avoid profiler failure when these values are not set in command line.

* v4.2 release.
This commit is contained in:
Junkai-Wu
2025-08-22 18:11:24 -04:00
committed by GitHub
parent 11cad1f67b
commit a49a78ffef
351 changed files with 28182 additions and 2032 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/README.md
+9
View File
@@ -1,5 +1,14 @@
# CUTLASS - Programming Examples
> [!IMPORTANT]
> ### ⚠️ **Not for Benchmarking!** ⚠️
>
> These examples are designed **solely for demonstrating CUTLASS functionality** and may **NOT optimized for performance benchmarking**.
>
> **For accurate performance measurements**, please use the **[CUTLASS Profiler](../tools/profiler/)** instead (recommended) or manually auto-tune the example, if unavailable via the profiler.
>
* [00_basic_gemm](00_basic_gemm/)
launches a basic GEMM with single precision inputs and outputs