v0.5.1

ruvnet/RuViewv0.5.1Sep 25, 2026by andimarafioti

Upgrading?

AI Summary

The CLI now automatically selects the GGML backend when CUDA is unavailable on Mac, and standard Apple Silicon installs now include the Metal runtime via `qwentts-cpp-python`.

Key Highlights

  • CLI selects GGML automatically when CUDA is unavailable on Mac.
  • Standard Apple Silicon install includes Metal runtime.
  • CUDA hosts still default to the Torch backend.
  • Explicit backend selection remains available.

New Features

  • Automatic GGML selection for Apple Silicon Macs
  • Metal runtime inclusion in standard Apple Silicon installs

Full Release Notes

## Fixes

- The CLI now selects GGML when CUDA is unavailable, so `faster-qwen3-tts custom ...` works on a supported Mac without `--backend ggml`. CUDA hosts still default to the Torch backend; explicit backend selection remains available.
- A standard install on native Apple Silicon now includes `qwentts-cpp-python>=0.4.1` and its Metal runtime. Other platforms still use the optional `ggml` extra.

Upgrade with `uv pip install -U faster-qwen3-tts`. The Metal wheel supports macOS 14+ on ARM64 Python; Intel Macs and Rosetta Python are outside its supported platforms.

## Changes

- [Make Apple Silicon GGML CLI work by default](https://github.com/andimarafioti/faster-qwen3-tts/pull/140)
- [Prepare release 0.5.1](https://github.com/andimarafioti/faster-qwen3-tts/pull/141)

[Full changelog](https://github.com/andimarafioti/faster-qwen3-tts/compare/v0.5.0...v0.5.1)

Related Repositories