3 people c9d8142a78 feat: add Blackwell GPU (sm_120) CUDA support (#401) ...

Set TORCH_CUDA_ARCH_LIST in the CUDA build step to include 12.0+PTX
for forward compatibility with Blackwell GPUs (RTX 5070 Ti, 5080, etc).

Pre-built PyTorch cu128 wheels only ship native kernels for sm_80/86/89/90.
Without this, Blackwell GPU users get "no kernel image is available for
execution on the device" at runtime.

Fixes #386
Related: #395, #396, #399, #400

Co-authored-by: Matt Van Horn <[email protected]>

2026-04-16 01:51:18 -07:00

..

assets

Update date formatting logic and replace binary assets

2026-01-26 01:10:22 -08:00

workflows

feat: add Blackwell GPU (sm_120) CUDA support (#401)

2026-04-16 01:51:18 -07:00