v0.5.1
rohitg00/agentmemoryv0.5.1Sep 25, 2026by andimarafioti
Upgrading?
AI Summary
Enhances Apple Silicon compatibility by automatically selecting the GGML backend when CUDA is unavailable, allowing `faster-qwen3-tts custom` to work natively on Mac without manual backend flags.
Key Highlights
- CLI now selects GGML automatically on native Apple Silicon
- Standard install includes `qwentts-cpp-python` and Metal runtime
- CUDA hosts still default to Torch backend
New Features
- Automatic backend selection on native Apple Silicon
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★ 392,696
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,067
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 357,683
Reverse engineer anything with agents, from app behavior down to native binaries.
anomalyco/opencode★ 219,670
The open source coding agent.
n8n-io/n8n★ 208,251
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.