v1.10.0 v0.1.7
cheaper-inference/OmniRouteMar 5, 2026 → Mar 23, 202618 days between releases
What's New
Replaced HuggingFace tokenizers with `tokie` for faster reranking initialization and reduced dependencies.
Breaking Changes
- Replaced HuggingFace `tokenizers` library with `tokie`
New Features
- Added `tokie` library for tokenizer reranking
Improvements
- Drastically faster tokenizer initialization
- Reduced transitive dependencies by ~260
- Removed runtime dependency on HuggingFace Hub
Upgrade Notes
No configuration changes are required. The tokenizer is now served from the CDN, removing the need for local HuggingFace Hub downloads.
The Two Releases
Version 1.10.0 - VibeVoice Lora Support, VibeVoice Preset Voices ( 0.5B model), Qwen3.5 LLM support
Mar 5, 2026· 8 months ago
A major update focusing on Voice AI training and LLM capabilities, specifically adding VibeVoice LoRA finetuning and Qwen3.5 support. It also includes significant UI refinements, Python 3.11 as the default, and audio denoising options.
Full release notesv0.1.7
Mar 23, 2026· 7 months ago
Replaced the HuggingFace tokenizers library with `tokie` to achieve massive performance improvements in reranking, reducing initialization time and dependencies while maintaining 100% accuracy.
Full release notes