From 2e55ae19e4745bf287530b9e806e145349030a4c Mon Sep 17 00:00:00 2001
From: Zhaohui Wang <173976389+GeoffreyWang1117@users.noreply.github.com>
Date: Thu, 6 Aug 2026 09:12:21 -0700
Subject: [PATCH] build: add sm_86 to the CUDA gencode list

The extension is currently built only for sm_89 (Ada) and sm_90 (Hopper),
so it fails to load on every Ampere consumer/datacenter GPU: RTX 3090,
RTX 3080 Ti, A10, A40. Those cards are what a lot of people prototype
sparse attention on.

Adding compute_86/sm_86 costs one more gencode pass at build time and
nothing at runtime.
---
 setup.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/setup.py b/setup.py
index e2723268..fe130d50 100644
--- a/setup.py
+++ b/setup.py
@@ -23,6 +23,7 @@
                 'cxx': ['-O3'],
                 'nvcc': [
                     '-O3',
+                    '-gencode=arch=compute_86,code=sm_86',
                     '-gencode=arch=compute_89,code=sm_89',
                     '-gencode=arch=compute_90,code=sm_90'
                 ],