Fix CUDA downloads on unsupported platforms (#770)

* Fix CUDA downloads on unsupported platforms

* fix: align CUDA status nullability

* fix: require CUDA download support flag
This commit is contained in:
Andrew Barnes
2026-07-20 19:22:18 -07:00
committed by GitHub
parent 258b92c9c0
commit 71b51366bc
7 changed files with 78 additions and 6 deletions
+2 -1
View File
@@ -75,7 +75,8 @@ No cloud fallback, no bring-your-own-API-key. Local is the product.
| Platform | Backend | Notes |
|----------|---------|-------|
| macOS (Apple Silicon) | MLX (Metal) | 4-5x faster via Neural Engine |
| Windows / Linux (NVIDIA) | PyTorch (CUDA) | Auto-downloads CUDA binary from within the app |
| Windows (NVIDIA) | PyTorch (CUDA) | Auto-downloads CUDA binary from within the app |
| Linux (NVIDIA) | PyTorch (CUDA) | Use a local/remote Python backend with CUDA PyTorch |
| Linux (AMD) | PyTorch (ROCm) | Auto-configures HSA_OVERRIDE_GFX_VERSION |
| Windows (any GPU) | DirectML | Universal Windows GPU support |
| Intel Arc | IPEX/XPU | Intel discrete GPU acceleration |