v0.5.1
CaviraOSS/LongMemoryv0.5.1Sep 25, 2026by andimarafioti
Upgrading?
AI Summary
Fixes Apple Silicon compatibility by automatically selecting the GGML backend when CUDA is unavailable and standardizing the inclusion of the Metal runtime.
Key Highlights
- CLI now selects GGML when CUDA is unavailable on Mac
- Standard install includes Metal runtime
- Explicit backend selection remains available
- Supports macOS 14+ on ARM64 Python
New Features
- Auto-selection of GGML backend on Apple Silicon
- Metal runtime inclusion in standard install
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
openclaw/openclaw★ 392,717
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,094
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 360,336
Reverse engineer anything with agents, from app behavior down to native binaries.
anomalyco/opencode★ 219,865
The open source coding agent.
n8n-io/n8n★ 208,278
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.