Update on "[Cutlass] Enable fusion with FusedSchedulerNodes"

mlazos · mlazos · commit 6685d543a338 · 2025-05-17T02:09:52.000-07:00
cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper zhuhaozhe blzheng wenzhe-nrv jiayisunx ipiszy chenyang78 kadeng muchulee8 amjames chauhang aakhundov

[ghstack-poisoned]
diff --git a/torch/_inductor/config.py b/torch/_inductor/config.py
@@ -1297,6 +1297,8 @@ class aot_inductor:
 
 
 class cuda:
+    """Settings for cuda backend, today this consists of cutlass"""
+
     # CUDA arch to use for CUDA template kernel compilation.
     # e.g. "70", "75", "80", "90", etc.
     # When arch is None, Inductor uses torch.cuda.get_device_capability(0).
