SageAttention cu130 / Torch 2.10 wheel missing SM120 architecture

Environment: Windows 11, RTX 5070 Ti (compute capability 12.0), Python 3.13.11, PyTorch 2.10.0+cu130.

The current sageattention-2.2.0+cu130torch2.10-cp313-cp313-win_amd64.whl fails on Blackwell with cudaErrorNoKernelImageForDevice for longer attention workloads.

packages/sageattention.yml has global arch_list: "8.0 9.0". The cu130/Torch 2.9 and Torch 2.11 combinations override this with "8.0 9.0 10.0 12.0", but the cu130/Torch 2.10 combination does not.

Inspecting the installed _fused.cp313-win_amd64.pyd and _qattn_sm89.cp313-win_amd64.pyd shows only sm_80 and sm_90a markers, with no sm_120/sm_120a.

Minimal reproduction with GQA 32:8, head_dim=128, L=4096 produces CUDA error: no kernel image is available for execution on the device, while L=128 works.

Adding arch_list: "8.0 9.0 10.0 12.0" to the cu130/Torch 2.10 matrix entry and rebuilding the wheel appears to be the expected fix.

Open packages/sageattention.yml and inspect the cu130/Torch 2.10 matrix entry alongside the cu130/Torch 2.9 and 2.11 overrides. Add the missing architecture setting, rebuild the Windows wheel, and verify that the resulting binaries include SM120 support for the reported PyTorch and Python versions.

Written by the indexing model from the issue text.