The open-source AI voice studio. Clone, dictate, create.
feat: add Blackwell GPU (sm_120) CUDA support (#401)
Matt Van Hornc9d8142a783b
diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex a3c224df..c3edd02c 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -203,6 +203,12 @@ jobs:- name: Build CUDA server binary (onedir)shell: bashworking-directory: backend+ env:+ # Include Blackwell (sm_120) via PTX forward compatibility.+ # Pre-built PyTorch cu128 wheels ship native kernels for sm_80/86/89/90+ # but not sm_120. Setting this env var causes torch.utils.cpp_extension+ # (and any JIT-compiled kernels) to target Blackwell GPUs as well.+ TORCH_CUDA_ARCH_LIST: "8.0;8.6;8.9;9.0;12.0+PTX"run: python build_binary.py --cuda- name: Package into server core + CUDA libs archives