From dd73ce388bdd930665609bf10b0370557f36bad7 Mon Sep 17 00:00:00 2001
From: LoserCheems <3314685395@qq.com>
Date: Sat, 20 Sep 2025 20:16:17 +0800
Subject: [PATCH 1/5] Updates architecture matrix to include only relevant
 architectures for wheel builds

---
 .github/workflows/publish.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index 38bdce0..2b5bd18 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -52,7 +52,7 @@ jobs:
         # Without this we get import error (undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs)
         # when building without C++11 ABI and using it on nvcr images.
         cxx11_abi: ["FALSE", "TRUE"]
-        arch: ["80", "86", "89", "90", "100", "120"]
+        arch: ["80", "90"]
         include:
             - torch-version: "2.9.0.dev20250904"
               cuda-version: "13.0"

From 26bd08de2a3a3966b52827b33ac8542cbb616e36 Mon Sep 17 00:00:00 2001
From: LoserCheems <3314685395@qq.com>
Date: Sat, 20 Sep 2025 20:16:50 +0800
Subject: [PATCH 2/5] Updates default CUDA architectures to include only
 relevant versions for builds

---
 setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/setup.py b/setup.py
index 8c847ac..99b875e 100644
--- a/setup.py
+++ b/setup.py
@@ -79,7 +79,7 @@ def should_skip_cuda_build():
 
 @functools.lru_cache(maxsize=None)
 def cuda_archs():
-    return os.getenv("FLASH_DMATTN_CUDA_ARCHS", "80;86;89;90;100;120").split(";")
+    return os.getenv("FLASH_DMATTN_CUDA_ARCHS", "80;90").split(";")
 
 
 def detect_preferred_sm_arch() -> Optional[str]:

From 735df584894c3529fe425d0e7bb31bbbfbf701ce Mon Sep 17 00:00:00 2001
From: LoserCheems <3314685395@qq.com>
Date: Sat, 20 Sep 2025 20:26:55 +0800
Subject: [PATCH 3/5] Refines build matrix by removing ARM64 OS and updating
 Python versions for compatibility

---
 .github/workflows/publish.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index 2b5bd18..8acf10d 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -43,8 +43,8 @@ jobs:
       matrix:
         # Using ubuntu-22.04 instead of 24.04 for more compatibility (glibc). Ideally we'd use the
         # manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
-        os: [ubuntu-22.04, ubuntu-22.04-arm64]
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+        os: [ubuntu-22.04]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
         torch-version: ["2.5.1", "2.6.0", "2.7.1", "2.8.0"]
         cuda-version: ["12.9.1"]
         # We need separate wheels that either uses C++11 ABI (-D_GLIBCXX_USE_CXX11_ABI) or not.

From 4d9cec0f9faddf5d5ba63fcddb2b6caedcf8eae3 Mon Sep 17 00:00:00 2001
From: LoserCheems <3314685395@qq.com>
Date: Sat, 20 Sep 2025 20:31:10 +0800
Subject: [PATCH 4/5] Refines Python and Torch version specifications for
 improved compatibility

---
 .github/workflows/publish.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index 8acf10d..76c50fb 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -44,8 +44,8 @@ jobs:
         # Using ubuntu-22.04 instead of 24.04 for more compatibility (glibc). Ideally we'd use the
         # manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
         os: [ubuntu-22.04]
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
-        torch-version: ["2.5.1", "2.6.0", "2.7.1", "2.8.0"]
+        python-version: ["3.9", "3.10", "3.12"]
+        torch-version: ["2.6.0", "2.7.1", "2.8.0"]
         cuda-version: ["12.9.1"]
         # We need separate wheels that either uses C++11 ABI (-D_GLIBCXX_USE_CXX11_ABI) or not.
         # Pytorch wheels currently don't use it, but nvcr images have Pytorch compiled with C++11 ABI.

From 2d7f6b658e8ea40f39580b5b5d5dca8533077dfd Mon Sep 17 00:00:00 2001
From: LoserCheems <3314685395@qq.com>
Date: Sat, 20 Sep 2025 20:32:57 +0800
Subject: [PATCH 5/5] Updates Python and Torch version specifications for
 improved compatibility

---
 .github/workflows/publish.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index 76c50fb..8acf10d 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -44,8 +44,8 @@ jobs:
         # Using ubuntu-22.04 instead of 24.04 for more compatibility (glibc). Ideally we'd use the
         # manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
         os: [ubuntu-22.04]
-        python-version: ["3.9", "3.10", "3.12"]
-        torch-version: ["2.6.0", "2.7.1", "2.8.0"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        torch-version: ["2.5.1", "2.6.0", "2.7.1", "2.8.0"]
         cuda-version: ["12.9.1"]
         # We need separate wheels that either uses C++11 ABI (-D_GLIBCXX_USE_CXX11_ABI) or not.
         # Pytorch wheels currently don't use it, but nvcr images have Pytorch compiled with C++11 ABI.