Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-09-18 14:20:42 -07:00
Code Issues Packages Projects Releases Wiki Activity

Fix CUDA downloads on unsupported platforms (#770)

Browse Source 
* 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 19:22:57 -07:00
committed by Jamie Pine
parent 3f4631c865
commit 12ce7a4c35
7 changed files with 78 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/content/docs/overview/gpu-acceleration.mdx
+2 -2
View File
@@ -23,7 +23,7 @@ This page is for the cases where it doesn't:
| **Windows + NVIDIA** | PyTorch CUDA (cu128) | Auto-downloads the CUDA backend binary on first use |
| **Windows + Intel Arc** | PyTorch XPU (IPEX) | New in 0.4 — works with Arc A-series and B-series |
| **Windows generic GPU** | DirectML | Universal Windows GPU support; slower than CUDA |
| **Linux + NVIDIA** | PyTorch CUDA (cu128) | Same auto-download flow as Windows |
| **Linux + NVIDIA** | PyTorch CUDA (cu128) | Use a local/remote Python backend with CUDA PyTorch |
| **Linux + AMD** | PyTorch ROCm | Auto-configures `HSA_OVERRIDE_GFX_VERSION` |
| **Linux + Intel Arc** | PyTorch XPU (IPEX) | |
| **Any (no GPU)** | PyTorch CPU | Works everywhere; expect 5-50x slower than GPU |
@@ -46,7 +46,7 @@ On M-series Macs, Voicebox ships an MLX-optimized backend that uses the Apple Ne
The Whisper Turbo + MLX combo dropped transcription latency from ~20s to ~2-3s on M-series chips (see CHANGELOG entry for v0.1.10).
## Windows / Linux + NVIDIA — The CUDA Backend Swap
## Windows + NVIDIA — The CUDA Backend Swap
Voicebox doesn't bundle CUDA into the main installer (it would balloon downloads to multi-gigabyte territory for users who don't have an NVIDIA GPU). Instead, when you first need it, the app downloads a separate **CUDA backend binary** that contains the PyTorch + CUDA runtime.
docs/content/docs/overview/introduction.mdx
+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 |